Index

_

__AUTHOR__ (in module lzero.config.meta) __AUTHOR_EMAIL__ (in module lzero.config.meta) __DESCRIPTION__ (in module lzero.config.meta) __init__() (lzero.agent.alphazero.AlphaZeroAgent method) (lzero.agent.efficientzero.EfficientZeroAgent method) (lzero.agent.gumbel_muzero.GumbelMuZeroAgent method) (lzero.agent.muzero.MuZeroAgent method) (lzero.agent.sampled_alphazero.SampledAlphaZeroAgent method) (lzero.agent.sampled_efficientzero.SampledEfficientZeroAgent method) (lzero.entry.eval_alphazero.eval_alphazero method) (lzero.entry.eval_muzero.eval_muzero method) (lzero.entry.eval_muzero_with_gym_env.eval_muzero_with_gym_env method) (lzero.entry.train_alphazero.train_alphazero method) (lzero.entry.train_muzero.train_muzero method) (lzero.entry.train_muzero_with_gym_env.train_muzero_with_gym_env method) (lzero.entry.train_muzero_with_reward_model.train_muzero_with_reward_model method) (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper method) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper method) (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) (lzero.mcts.tree_search.mcts_ctree.EfficientZeroMCTSCtree method) (lzero.mcts.tree_search.mcts_ctree.GumbelMuZeroMCTSCtree method) (lzero.mcts.tree_search.mcts_ctree.MuZeroMCTSCtree method) (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.FeatureAndGradientHook method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.OnehotArgmax method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) (lzero.worker.muzero_collector.MuZeroCollector method) (lzero.worker.muzero_evaluator.MuZeroEvaluator method) __TITLE__ (in module lzero.config.meta) __VERSION__ (in module lzero.config.meta) _abc_impl (lzero.mcts.buffer.game_buffer.GameBuffer attribute) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer attribute) (lzero.policy.alphazero.AlphaZeroPolicy attribute) (lzero.policy.efficientzero.EfficientZeroPolicy attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy attribute) (lzero.policy.muzero.MuZeroPolicy attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy attribute) (lzero.policy.unizero.UniZeroPolicy attribute) (lzero.worker.muzero_collector.MuZeroCollector attribute) (lzero.worker.muzero_evaluator.MuZeroEvaluator attribute) _afterstate_dynamics() (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _afterstate_prediction() (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _apply() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _asdict() (lzero.policy.alphazero.AlphaZeroPolicy.collect_function method) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function method) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function method) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function method) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function method) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function method) (lzero.policy.muzero.MuZeroPolicy.collect_function method) (lzero.policy.muzero.MuZeroPolicy.eval_function method) (lzero.policy.muzero.MuZeroPolicy.learn_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function method) (lzero.policy.unizero.UniZeroPolicy.collect_function method) (lzero.policy.unizero.UniZeroPolicy.eval_function method) (lzero.policy.unizero.UniZeroPolicy.learn_function method) _backward_cls (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) _backward_hooks (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _backward_pre_hooks (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _buffers (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _calculate_policy_loss_cont() (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) _calculate_policy_loss_disc() (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) _call_impl() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _compiled_autograd_backward_state (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) _compiled_autograd_key() (lzero.model.stochastic_muzero_model.OnehotArgmax static method) _compiled_call_impl (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _compute_priorities() (lzero.worker.muzero_collector.MuZeroCollector method) _compute_target_policy_non_reanalyzed() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _compute_target_policy_reanalyzed() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _compute_target_reward_value() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _create_model() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _dynamics() (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _field_defaults (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function attribute) (lzero.policy.muzero.MuZeroPolicy.collect_function attribute) (lzero.policy.muzero.MuZeroPolicy.eval_function attribute) (lzero.policy.muzero.MuZeroPolicy.learn_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function attribute) (lzero.policy.unizero.UniZeroPolicy.collect_function attribute) (lzero.policy.unizero.UniZeroPolicy.eval_function attribute) (lzero.policy.unizero.UniZeroPolicy.learn_function attribute) _fields (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function attribute) (lzero.policy.muzero.MuZeroPolicy.collect_function attribute) (lzero.policy.muzero.MuZeroPolicy.eval_function attribute) (lzero.policy.muzero.MuZeroPolicy.learn_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function attribute) (lzero.policy.unizero.UniZeroPolicy.collect_function attribute) (lzero.policy.unizero.UniZeroPolicy.eval_function attribute) (lzero.policy.unizero.UniZeroPolicy.learn_function attribute) _forward_collect() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _forward_eval() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _forward_hooks (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _forward_hooks_always_called (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _forward_hooks_with_kwargs (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _forward_learn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _forward_pre_hooks (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _forward_pre_hooks_with_kwargs (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _get_attribute() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _get_backward_hooks() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _get_backward_pre_hooks() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _get_batch_size() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _get_compiled_autograd_symints() (lzero.model.stochastic_muzero_model.OnehotArgmax method) _get_n_episode() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _get_n_sample() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _get_name() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _get_simulation_env() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _get_target_obs_index_in_step_k() (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _get_train_sample() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _init_collect() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _init_eval() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _init_learn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _init_multi_gpu_setting() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _input_metadata (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) _is_compiled_autograd_tracing() (lzero.model.stochastic_muzero_model.OnehotArgmax method) _is_full_backward_hook (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute)

_is_protocol (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper attribute) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper attribute) _load_from_state_dict() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _load_state_dict_collect() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _load_state_dict_eval() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _load_state_dict_learn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _load_state_dict_post_hooks (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _load_state_dict_pre_hooks (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _make() (lzero.policy.alphazero.AlphaZeroPolicy.collect_function class method) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function class method) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function class method) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function class method) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function class method) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function class method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function class method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function class method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function class method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function class method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function class method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function class method) (lzero.policy.muzero.MuZeroPolicy.collect_function class method) (lzero.policy.muzero.MuZeroPolicy.eval_function class method) (lzero.policy.muzero.MuZeroPolicy.learn_function class method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function class method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function class method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function class method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function class method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function class method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function class method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function class method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function class method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function class method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function class method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function class method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function class method) (lzero.policy.unizero.UniZeroPolicy.collect_function class method) (lzero.policy.unizero.UniZeroPolicy.eval_function class method) (lzero.policy.unizero.UniZeroPolicy.learn_function class method) _make_batch() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _make_batch_for_reanalyze() (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _materialize_non_diff_grads (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) _maybe_warn_non_full_backward_hook() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _modules (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _monitor_vars_learn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _named_members() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _non_persistent_buffers_set (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _np_random (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper property) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper property) _output_log() (lzero.worker.muzero_collector.MuZeroCollector method) _parameters (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _policy_value_fn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) _policy_value_func() (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _prediction() (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _prepare_policy_non_reanalyzed_context() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _prepare_policy_reanalyzed_context() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _prepare_reward_value_context() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _preprocess_to_play_and_action_mask() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _process_transition() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _push_game_segment() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _raw_saved_tensors (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) _register_hook() (lzero.model.stochastic_muzero_model.OnehotArgmax static method) _register_hook_dict() (lzero.model.stochastic_muzero_model.OnehotArgmax method) _register_load_state_dict_pre_hook() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _register_state_dict_hook() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _remove() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _replace() (lzero.policy.alphazero.AlphaZeroPolicy.collect_function method) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function method) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function method) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function method) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function method) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function method) (lzero.policy.muzero.MuZeroPolicy.collect_function method) (lzero.policy.muzero.MuZeroPolicy.eval_function method) (lzero.policy.muzero.MuZeroPolicy.learn_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function method) (lzero.policy.unizero.UniZeroPolicy.collect_function method) (lzero.policy.unizero.UniZeroPolicy.eval_function method) (lzero.policy.unizero.UniZeroPolicy.learn_function method) _replicate_for_data_parallel() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _representation() (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _reset_collect() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _reset_eval() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _reset_learn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _reset_stat() (lzero.worker.muzero_collector.MuZeroCollector method) _sample_orig_data() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _sample_orig_data_episode() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _sample_orig_reanalyze_batch() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _sample_orig_reanalyze_data() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _save_to_state_dict() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _sequence_nr() (lzero.model.stochastic_muzero_model.OnehotArgmax method) _set_attribute() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _set_sequence_nr() (lzero.model.stochastic_muzero_model.OnehotArgmax method) _slow_forward() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) _state_dict_collect() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _state_dict_eval() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _state_dict_hooks (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _state_dict_learn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) _state_dict_pre_hooks (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _version (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) _wrapped_call_impl() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

A

action_space (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper property) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper property) ActionDiscretizationEnvWrapper (class in lzero.envs.wrappers.action_discretization_env_wrapper) add_module() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) AfterstatePredictionNetwork (class in lzero.model.stochastic_muzero_model) AlphaZeroAgent (class in lzero.agent.alphazero) AlphaZeroModel (class in lzero.model.alphazero_model)

AlphaZeroPolicy (class in lzero.policy.alphazero) AlphaZeroPolicy.collect_function (class in lzero.policy.alphazero) AlphaZeroPolicy.eval_function (class in lzero.policy.alphazero) AlphaZeroPolicy.learn_function (class in lzero.policy.alphazero) analyze() (lzero.model.common.FeatureAndGradientHook method) apply() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.OnehotArgmax class method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

B

backward() (lzero.model.stochastic_muzero_model.OnehotArgmax static method) backward_hook() (lzero.model.common.FeatureAndGradientHook method) batch_evaluate() (lzero.agent.alphazero.AlphaZeroAgent method) (lzero.agent.efficientzero.EfficientZeroAgent method) (lzero.agent.gumbel_muzero.GumbelMuZeroAgent method) (lzero.agent.muzero.MuZeroAgent method) (lzero.agent.sampled_alphazero.SampledAlphaZeroAgent method) (lzero.agent.sampled_efficientzero.SampledEfficientZeroAgent method) best (lzero.agent.alphazero.AlphaZeroAgent property) (lzero.agent.efficientzero.EfficientZeroAgent property) (lzero.agent.gumbel_muzero.GumbelMuZeroAgent property) (lzero.agent.muzero.MuZeroAgent property) (lzero.agent.sampled_alphazero.SampledAlphaZeroAgent property) (lzero.agent.sampled_efficientzero.SampledEfficientZeroAgent property) bfloat16() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

buffers() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

C

call_super_init (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) cfg (lzero.policy.alphazero.AlphaZeroPolicy property) (lzero.policy.efficientzero.EfficientZeroPolicy property) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy property) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy property) (lzero.policy.muzero.MuZeroPolicy property) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy property) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy property) (lzero.policy.sampled_muzero.SampledMuZeroPolicy property) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy property) (lzero.policy.unizero.UniZeroPolicy property) chance_encode() (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) ChanceEncoder (class in lzero.model.stochastic_muzero_model) ChanceEncoderBackbone (class in lzero.model.stochastic_muzero_model) ChanceEncoderBackboneMLP (class in lzero.model.stochastic_muzero_model) children() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) class_name() (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper class method) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper class method) clear_data() (lzero.model.common.FeatureAndGradientHook method) close() (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper method) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper method) (lzero.worker.muzero_collector.MuZeroCollector method) (lzero.worker.muzero_evaluator.MuZeroEvaluator method) collect() (lzero.worker.muzero_collector.MuZeroCollector method) collect_mode (lzero.policy.alphazero.AlphaZeroPolicy property) (lzero.policy.efficientzero.EfficientZeroPolicy property) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy property) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy property) (lzero.policy.muzero.MuZeroPolicy property) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy property) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy property) (lzero.policy.sampled_muzero.SampledMuZeroPolicy property) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy property) (lzero.policy.unizero.UniZeroPolicy property) compile() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

compute_logp_value() (lzero.model.alphazero_model.AlphaZeroModel method) compute_policy_value() (lzero.model.alphazero_model.AlphaZeroModel method) config (lzero.mcts.buffer.game_buffer.GameBuffer attribute) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer attribute) (lzero.mcts.tree_search.mcts_ctree.EfficientZeroMCTSCtree attribute) (lzero.mcts.tree_search.mcts_ctree.GumbelMuZeroMCTSCtree attribute) (lzero.mcts.tree_search.mcts_ctree.MuZeroMCTSCtree attribute) (lzero.policy.alphazero.AlphaZeroPolicy attribute) (lzero.policy.efficientzero.EfficientZeroPolicy attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy attribute) (lzero.policy.muzero.MuZeroPolicy attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy attribute) (lzero.policy.unizero.UniZeroPolicy attribute) (lzero.worker.muzero_collector.MuZeroCollector attribute) (lzero.worker.muzero_evaluator.MuZeroEvaluator attribute) count() (lzero.policy.alphazero.AlphaZeroPolicy.collect_function method) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function method) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function method) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function method) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function method) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function method) (lzero.policy.muzero.MuZeroPolicy.collect_function method) (lzero.policy.muzero.MuZeroPolicy.eval_function method) (lzero.policy.muzero.MuZeroPolicy.learn_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function method) (lzero.policy.unizero.UniZeroPolicy.collect_function method) (lzero.policy.unizero.UniZeroPolicy.eval_function method) (lzero.policy.unizero.UniZeroPolicy.learn_function method) cpu() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) cuda() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

D

default_config() (lzero.mcts.buffer.game_buffer.GameBuffer class method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer class method) (lzero.mcts.tree_search.mcts_ctree.EfficientZeroMCTSCtree class method) (lzero.mcts.tree_search.mcts_ctree.GumbelMuZeroMCTSCtree class method) (lzero.mcts.tree_search.mcts_ctree.MuZeroMCTSCtree class method) (lzero.policy.alphazero.AlphaZeroPolicy class method) (lzero.policy.efficientzero.EfficientZeroPolicy class method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy class method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy class method) (lzero.policy.muzero.MuZeroPolicy class method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy class method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy class method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy class method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy class method) (lzero.policy.unizero.UniZeroPolicy class method) (lzero.worker.muzero_collector.MuZeroCollector class method) (lzero.worker.muzero_evaluator.MuZeroEvaluator class method) default_model() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method) deploy() (lzero.agent.alphazero.AlphaZeroAgent method) (lzero.agent.efficientzero.EfficientZeroAgent method) (lzero.agent.gumbel_muzero.GumbelMuZeroAgent method) (lzero.agent.muzero.MuZeroAgent method) (lzero.agent.sampled_alphazero.SampledAlphaZeroAgent method) (lzero.agent.sampled_efficientzero.SampledEfficientZeroAgent method) dirty_tensors (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) double() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

DownSample (class in lzero.model.common) dump_patches (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) DynamicsNetwork (class in lzero.model.efficientzero_model) (class in lzero.model.muzero_model) (class in lzero.model.muzero_model_mlp) (class in lzero.model.stochastic_muzero_model) DynamicsNetworkMLP (class in lzero.model.efficientzero_model_mlp)

E

EfficientZeroAgent (class in lzero.agent.efficientzero) EfficientZeroMCTSCtree (class in lzero.mcts.tree_search.mcts_ctree) EfficientZeroPolicy (class in lzero.policy.efficientzero) EfficientZeroPolicy.collect_function (class in lzero.policy.efficientzero) EfficientZeroPolicy.eval_function (class in lzero.policy.efficientzero) EfficientZeroPolicy.learn_function (class in lzero.policy.efficientzero) envstep (lzero.worker.muzero_collector.MuZeroCollector property) eval() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) (lzero.worker.muzero_evaluator.MuZeroEvaluator method) eval_alphazero (class in lzero.entry.eval_alphazero) eval_mode (lzero.policy.alphazero.AlphaZeroPolicy property) (lzero.policy.efficientzero.EfficientZeroPolicy property) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy property) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy property) (lzero.policy.muzero.MuZeroPolicy property) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy property) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy property) (lzero.policy.sampled_muzero.SampledMuZeroPolicy property) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy property) (lzero.policy.unizero.UniZeroPolicy property)

eval_muzero (class in lzero.entry.eval_muzero) eval_muzero_with_gym_env (class in lzero.entry.eval_muzero_with_gym_env) extra_repr() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

F

FeatureAndGradientHook (class in lzero.model.common) float() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) forward (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function attribute) (lzero.policy.muzero.MuZeroPolicy.collect_function attribute) (lzero.policy.muzero.MuZeroPolicy.eval_function attribute) (lzero.policy.muzero.MuZeroPolicy.learn_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function attribute) (lzero.policy.unizero.UniZeroPolicy.collect_function attribute) (lzero.policy.unizero.UniZeroPolicy.eval_function attribute) (lzero.policy.unizero.UniZeroPolicy.learn_function attribute)

forward() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.OnehotArgmax static method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) forward_hook() (lzero.model.common.FeatureAndGradientHook method)

G

GameBuffer (class in lzero.mcts.buffer.game_buffer) generate_vmap_rule (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) get_attribute (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function attribute) (lzero.policy.muzero.MuZeroPolicy.collect_function attribute) (lzero.policy.muzero.MuZeroPolicy.eval_function attribute) (lzero.policy.muzero.MuZeroPolicy.learn_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function attribute) (lzero.policy.unizero.UniZeroPolicy.collect_function attribute) (lzero.policy.unizero.UniZeroPolicy.eval_function attribute) (lzero.policy.unizero.UniZeroPolicy.learn_function attribute) get_buffer() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) get_dynamic_mean() (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) get_extra_state() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

get_num_of_episodes() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) get_num_of_game_segments() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) get_num_of_transitions() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) get_parameter() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) get_params_mean() (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) get_reward_mean() (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) get_submodule() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) get_train_sample (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function attribute) (lzero.policy.muzero.MuZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function attribute) (lzero.policy.unizero.UniZeroPolicy.collect_function attribute) GumbelAlphaZeroPolicy (class in lzero.policy.gumbel_alphazero) GumbelAlphaZeroPolicy.collect_function (class in lzero.policy.gumbel_alphazero) GumbelAlphaZeroPolicy.eval_function (class in lzero.policy.gumbel_alphazero) GumbelAlphaZeroPolicy.learn_function (class in lzero.policy.gumbel_alphazero) GumbelMuZeroAgent (class in lzero.agent.gumbel_muzero) GumbelMuZeroMCTSCtree (class in lzero.mcts.tree_search.mcts_ctree) GumbelMuZeroPolicy (class in lzero.policy.gumbel_muzero) GumbelMuZeroPolicy.collect_function (class in lzero.policy.gumbel_muzero) GumbelMuZeroPolicy.eval_function (class in lzero.policy.gumbel_muzero) GumbelMuZeroPolicy.learn_function (class in lzero.policy.gumbel_muzero)

H

half() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

I

index() (lzero.policy.alphazero.AlphaZeroPolicy.collect_function method) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function method) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function method) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function method) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function method) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function method) (lzero.policy.muzero.MuZeroPolicy.collect_function method) (lzero.policy.muzero.MuZeroPolicy.eval_function method) (lzero.policy.muzero.MuZeroPolicy.learn_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function method) (lzero.policy.unizero.UniZeroPolicy.collect_function method) (lzero.policy.unizero.UniZeroPolicy.eval_function method) (lzero.policy.unizero.UniZeroPolicy.learn_function method) info (lzero.policy.alphazero.AlphaZeroPolicy.learn_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function attribute) (lzero.policy.muzero.MuZeroPolicy.learn_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function attribute) (lzero.policy.unizero.UniZeroPolicy.learn_function attribute)

initial_inference() (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) ipu() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

J

jvp() (lzero.model.stochastic_muzero_model.OnehotArgmax static method)

L

LatentDecoder (class in lzero.model.common) LatentDecoderForMemoryEnv (class in lzero.model.common) LatentEncoderForMemoryEnv (class in lzero.model.common) learn_mode (lzero.policy.alphazero.AlphaZeroPolicy property) (lzero.policy.efficientzero.EfficientZeroPolicy property) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy property) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy property) (lzero.policy.muzero.MuZeroPolicy property) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy property) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy property) (lzero.policy.sampled_muzero.SampledMuZeroPolicy property) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy property) (lzero.policy.unizero.UniZeroPolicy property) LightZeroEnvWrapper (class in lzero.envs.wrappers.lightzero_env_wrapper) load_state_dict (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function attribute) (lzero.policy.muzero.MuZeroPolicy.collect_function attribute) (lzero.policy.muzero.MuZeroPolicy.eval_function attribute) (lzero.policy.muzero.MuZeroPolicy.learn_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function attribute) (lzero.policy.unizero.UniZeroPolicy.collect_function attribute) (lzero.policy.unizero.UniZeroPolicy.eval_function attribute) (lzero.policy.unizero.UniZeroPolicy.learn_function attribute)

load_state_dict() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) lzero.config.meta module

M

mark_dirty() (lzero.model.stochastic_muzero_model.OnehotArgmax method) mark_non_differentiable() (lzero.model.stochastic_muzero_model.OnehotArgmax method) mark_shared_storage() (lzero.model.stochastic_muzero_model.OnehotArgmax method) materialize_grads (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) maybe_clear_saved_tensors() (lzero.model.stochastic_muzero_model.OnehotArgmax method) metadata (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper property) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper property) (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) module lzero.config.meta modules() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) monitor_vars (lzero.policy.alphazero.AlphaZeroPolicy.learn_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function attribute) (lzero.policy.muzero.MuZeroPolicy.learn_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function attribute) (lzero.policy.unizero.UniZeroPolicy.learn_function attribute)

monitor_weights_and_grads() (lzero.policy.unizero.UniZeroPolicy method) mtia() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) MuZeroAgent (class in lzero.agent.muzero) MuZeroCollector (class in lzero.worker.muzero_collector) MuZeroEvaluator (class in lzero.worker.muzero_evaluator) MuZeroGameBuffer (class in lzero.mcts.buffer.game_buffer_muzero) MuZeroMCTSCtree (class in lzero.mcts.tree_search.mcts_ctree) MuZeroModel (class in lzero.model.muzero_model) MuZeroModelMLP (class in lzero.model.muzero_model_mlp) MuZeroPolicy (class in lzero.policy.muzero) MuZeroPolicy.collect_function (class in lzero.policy.muzero) MuZeroPolicy.eval_function (class in lzero.policy.muzero) MuZeroPolicy.learn_function (class in lzero.policy.muzero)

N

name() (lzero.model.stochastic_muzero_model.OnehotArgmax method) named_buffers() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) named_children() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) named_modules() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

named_parameters() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) needs_input_grad (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) next_functions (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) non_differentiable (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) np_random (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper property) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper property)

O

observation_space (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper property) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper property)

OnehotArgmax (class in lzero.model.stochastic_muzero_model)

P

pad_and_save_last_trajectory() (lzero.worker.muzero_collector.MuZeroCollector method) parameters() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

PredictionHiddenNetwork (class in lzero.model.common) PredictionNetwork (class in lzero.model.alphazero_model) (class in lzero.model.common) (class in lzero.model.sampled_efficientzero_model) PredictionNetworkMLP (class in lzero.model.common) (class in lzero.model.sampled_efficientzero_model_mlp) process_transition (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function attribute) (lzero.policy.muzero.MuZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function attribute) (lzero.policy.unizero.UniZeroPolicy.collect_function attribute) project() (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) push_game_segments() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method)

R

reanalyze_buffer() (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) recompute_pos_emb_diff_and_clear_cache() (lzero.policy.unizero.UniZeroPolicy method) recurrent_inference() (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) register_backward_hook() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) register_buffer() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) register_forward_hook() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) register_forward_pre_hook() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) register_full_backward_hook() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) register_full_backward_pre_hook() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) register_hook() (lzero.model.stochastic_muzero_model.OnehotArgmax method) register_load_state_dict_post_hook() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) register_load_state_dict_pre_hook() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

register_module() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) register_parameter() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) register_prehook() (lzero.model.stochastic_muzero_model.OnehotArgmax method) register_state_dict_post_hook() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) register_state_dict_pre_hook() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) remove_hooks() (lzero.model.common.FeatureAndGradientHook method) remove_oldest_data_to_fit() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) render() (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper method) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper method) render_mode (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper property) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper property) RepresentationNetwork (class in lzero.model.common) RepresentationNetworkMLP (class in lzero.model.common) RepresentationNetworkUniZero (class in lzero.model.common) requires_grad (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) requires_grad_() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) reset (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function attribute) (lzero.policy.muzero.MuZeroPolicy.collect_function attribute) (lzero.policy.muzero.MuZeroPolicy.eval_function attribute) (lzero.policy.muzero.MuZeroPolicy.learn_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function attribute) (lzero.policy.unizero.UniZeroPolicy.collect_function attribute) (lzero.policy.unizero.UniZeroPolicy.eval_function attribute) (lzero.policy.unizero.UniZeroPolicy.learn_function attribute) reset() (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper method) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper method) (lzero.worker.muzero_collector.MuZeroCollector method) (lzero.worker.muzero_evaluator.MuZeroEvaluator method) reset_env() (lzero.worker.muzero_collector.MuZeroCollector method) (lzero.worker.muzero_evaluator.MuZeroEvaluator method) reset_policy() (lzero.worker.muzero_collector.MuZeroCollector method) (lzero.worker.muzero_evaluator.MuZeroEvaluator method) reset_runtime_metrics() (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) reward_range (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper property) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper property) roots() (lzero.mcts.tree_search.mcts_ctree.EfficientZeroMCTSCtree class method) (lzero.mcts.tree_search.mcts_ctree.GumbelMuZeroMCTSCtree class method) (lzero.mcts.tree_search.mcts_ctree.MuZeroMCTSCtree class method)

S

sample() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) SampledAlphaZeroAgent (class in lzero.agent.sampled_alphazero) SampledAlphaZeroPolicy (class in lzero.policy.sampled_alphazero) SampledAlphaZeroPolicy.collect_function (class in lzero.policy.sampled_alphazero) SampledAlphaZeroPolicy.eval_function (class in lzero.policy.sampled_alphazero) SampledAlphaZeroPolicy.learn_function (class in lzero.policy.sampled_alphazero) SampledEfficientZeroAgent (class in lzero.agent.sampled_efficientzero) SampledEfficientZeroPolicy (class in lzero.policy.sampled_efficientzero) SampledEfficientZeroPolicy.collect_function (class in lzero.policy.sampled_efficientzero) SampledEfficientZeroPolicy.eval_function (class in lzero.policy.sampled_efficientzero) SampledEfficientZeroPolicy.learn_function (class in lzero.policy.sampled_efficientzero) SampledMuZeroPolicy (class in lzero.policy.sampled_muzero) SampledMuZeroPolicy.collect_function (class in lzero.policy.sampled_muzero) SampledMuZeroPolicy.eval_function (class in lzero.policy.sampled_muzero) SampledMuZeroPolicy.learn_function (class in lzero.policy.sampled_muzero) save_for_backward() (lzero.model.stochastic_muzero_model.OnehotArgmax method) save_for_forward() (lzero.model.stochastic_muzero_model.OnehotArgmax method) saved_for_forward (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) saved_tensors (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) saved_variables (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) search() (lzero.mcts.tree_search.mcts_ctree.EfficientZeroMCTSCtree method) (lzero.mcts.tree_search.mcts_ctree.GumbelMuZeroMCTSCtree method) (lzero.mcts.tree_search.mcts_ctree.MuZeroMCTSCtree method) search_with_reuse() (lzero.mcts.tree_search.mcts_ctree.EfficientZeroMCTSCtree method) (lzero.mcts.tree_search.mcts_ctree.MuZeroMCTSCtree method) seed() (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper method) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper method) set_attribute (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function attribute) (lzero.policy.muzero.MuZeroPolicy.collect_function attribute) (lzero.policy.muzero.MuZeroPolicy.eval_function attribute) (lzero.policy.muzero.MuZeroPolicy.learn_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function attribute) (lzero.policy.unizero.UniZeroPolicy.collect_function attribute) (lzero.policy.unizero.UniZeroPolicy.eval_function attribute) (lzero.policy.unizero.UniZeroPolicy.learn_function attribute) set_extra_state() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) set_materialize_grads() (lzero.model.stochastic_muzero_model.OnehotArgmax method) set_submodule() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) set_train_iter_env_step() (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method)

setup_context() (lzero.model.stochastic_muzero_model.OnehotArgmax static method) setup_hooks() (lzero.model.common.FeatureAndGradientHook method) share_memory() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) should_eval() (lzero.worker.muzero_evaluator.MuZeroEvaluator method) SimNorm (class in lzero.model.common) spec (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper property) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper property) state_dict (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.learn_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.collect_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.eval_function attribute) (lzero.policy.efficientzero.EfficientZeroPolicy.learn_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.collect_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.eval_function attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy.learn_function attribute) (lzero.policy.muzero.MuZeroPolicy.collect_function attribute) (lzero.policy.muzero.MuZeroPolicy.eval_function attribute) (lzero.policy.muzero.MuZeroPolicy.learn_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.collect_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.eval_function attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy.learn_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.collect_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.eval_function attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy.learn_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.collect_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.eval_function attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy.learn_function attribute) (lzero.policy.unizero.UniZeroPolicy.collect_function attribute) (lzero.policy.unizero.UniZeroPolicy.eval_function attribute) (lzero.policy.unizero.UniZeroPolicy.learn_function attribute) state_dict() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) step() (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper method) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper method) StochasticMuZeroModel (class in lzero.model.stochastic_muzero_model) StochasticMuZeroModelMLP (class in lzero.model.stochastic_muzero_model_mlp) StochasticMuZeroPolicy (class in lzero.policy.stochastic_muzero) StochasticMuZeroPolicy.collect_function (class in lzero.policy.stochastic_muzero) StochasticMuZeroPolicy.eval_function (class in lzero.policy.stochastic_muzero) StochasticMuZeroPolicy.learn_function (class in lzero.policy.stochastic_muzero) StraightThroughEstimator (class in lzero.model.stochastic_muzero_model) supported_env_list (lzero.agent.alphazero.AlphaZeroAgent attribute) (lzero.agent.efficientzero.EfficientZeroAgent attribute) (lzero.agent.gumbel_muzero.GumbelMuZeroAgent attribute) (lzero.agent.muzero.MuZeroAgent attribute) (lzero.agent.sampled_alphazero.SampledAlphaZeroAgent attribute) (lzero.agent.sampled_efficientzero.SampledEfficientZeroAgent attribute) sync_gradients() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.efficientzero.EfficientZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy method) (lzero.policy.muzero.MuZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy method) (lzero.policy.sampled_muzero.SampledMuZeroPolicy method) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy method) (lzero.policy.unizero.UniZeroPolicy method)

T

T_destination (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) to() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) to_empty() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) to_save (lzero.model.stochastic_muzero_model.OnehotArgmax attribute) total_field (lzero.policy.alphazero.AlphaZeroPolicy attribute) (lzero.policy.efficientzero.EfficientZeroPolicy attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy attribute) (lzero.policy.gumbel_muzero.GumbelMuZeroPolicy attribute) (lzero.policy.muzero.MuZeroPolicy attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy attribute) (lzero.policy.sampled_efficientzero.SampledEfficientZeroPolicy attribute) (lzero.policy.sampled_muzero.SampledMuZeroPolicy attribute) (lzero.policy.stochastic_muzero.StochasticMuZeroPolicy attribute) (lzero.policy.unizero.UniZeroPolicy attribute)

train() (lzero.agent.alphazero.AlphaZeroAgent method) (lzero.agent.efficientzero.EfficientZeroAgent method) (lzero.agent.gumbel_muzero.GumbelMuZeroAgent method) (lzero.agent.muzero.MuZeroAgent method) (lzero.agent.sampled_alphazero.SampledAlphaZeroAgent method) (lzero.agent.sampled_efficientzero.SampledEfficientZeroAgent method) (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method) train_alphazero (class in lzero.entry.train_alphazero) train_muzero (class in lzero.entry.train_muzero) train_muzero_with_gym_env (class in lzero.entry.train_muzero_with_gym_env) train_muzero_with_reward_model (class in lzero.entry.train_muzero_with_reward_model) training (lzero.model.alphazero_model.AlphaZeroModel attribute) (lzero.model.alphazero_model.PredictionNetwork attribute) (lzero.model.common.DownSample attribute) (lzero.model.common.LatentDecoder attribute) (lzero.model.common.LatentDecoderForMemoryEnv attribute) (lzero.model.common.LatentEncoderForMemoryEnv attribute) (lzero.model.common.PredictionHiddenNetwork attribute) (lzero.model.common.PredictionNetwork attribute) (lzero.model.common.PredictionNetworkMLP attribute) (lzero.model.common.RepresentationNetwork attribute) (lzero.model.common.RepresentationNetworkMLP attribute) (lzero.model.common.RepresentationNetworkUniZero attribute) (lzero.model.common.SimNorm attribute) (lzero.model.common.VectorDecoderForMemoryEnv attribute) (lzero.model.efficientzero_model.DynamicsNetwork attribute) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP attribute) (lzero.model.muzero_model.DynamicsNetwork attribute) (lzero.model.muzero_model.MuZeroModel attribute) (lzero.model.muzero_model_mlp.DynamicsNetwork attribute) (lzero.model.muzero_model_mlp.MuZeroModelMLP attribute) (lzero.model.sampled_efficientzero_model.PredictionNetwork attribute) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP attribute) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork attribute) (lzero.model.stochastic_muzero_model.ChanceEncoder attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone attribute) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP attribute) (lzero.model.stochastic_muzero_model.DynamicsNetwork attribute) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel attribute) (lzero.model.stochastic_muzero_model.StraightThroughEstimator attribute) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP attribute) type() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

U

UniZeroPolicy (class in lzero.policy.unizero) UniZeroPolicy.collect_function (class in lzero.policy.unizero) UniZeroPolicy.eval_function (class in lzero.policy.unizero) UniZeroPolicy.learn_function (class in lzero.policy.unizero)

unwrapped (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper property) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper property) update_priority() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method)

V

VectorDecoderForMemoryEnv (class in lzero.model.common)

vjp() (lzero.model.stochastic_muzero_model.OnehotArgmax static method) vmap() (lzero.model.stochastic_muzero_model.OnehotArgmax static method)

X

xpu() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)

Z

zero_grad() (lzero.model.alphazero_model.AlphaZeroModel method) (lzero.model.alphazero_model.PredictionNetwork method) (lzero.model.common.DownSample method) (lzero.model.common.LatentDecoder method) (lzero.model.common.LatentDecoderForMemoryEnv method) (lzero.model.common.LatentEncoderForMemoryEnv method) (lzero.model.common.PredictionHiddenNetwork method) (lzero.model.common.PredictionNetwork method) (lzero.model.common.PredictionNetworkMLP method) (lzero.model.common.RepresentationNetwork method) (lzero.model.common.RepresentationNetworkMLP method) (lzero.model.common.RepresentationNetworkUniZero method) (lzero.model.common.SimNorm method) (lzero.model.common.VectorDecoderForMemoryEnv method) (lzero.model.efficientzero_model.DynamicsNetwork method) (lzero.model.efficientzero_model_mlp.DynamicsNetworkMLP method) (lzero.model.muzero_model.DynamicsNetwork method) (lzero.model.muzero_model.MuZeroModel method) (lzero.model.muzero_model_mlp.DynamicsNetwork method) (lzero.model.muzero_model_mlp.MuZeroModelMLP method) (lzero.model.sampled_efficientzero_model.PredictionNetwork method) (lzero.model.sampled_efficientzero_model_mlp.PredictionNetworkMLP method) (lzero.model.stochastic_muzero_model.AfterstatePredictionNetwork method) (lzero.model.stochastic_muzero_model.ChanceEncoder method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackbone method) (lzero.model.stochastic_muzero_model.ChanceEncoderBackboneMLP method) (lzero.model.stochastic_muzero_model.DynamicsNetwork method) (lzero.model.stochastic_muzero_model.StochasticMuZeroModel method) (lzero.model.stochastic_muzero_model.StraightThroughEstimator method) (lzero.model.stochastic_muzero_model_mlp.StochasticMuZeroModelMLP method)