Index

_

__AUTHOR__ (in module lzero.config.meta) __AUTHOR_EMAIL__ (in module lzero.config.meta) __DESCRIPTION__ (in module lzero.config.meta) __init__() (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.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy 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.gumbel_alphazero.GumbelAlphaZeroPolicy attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy attribute) (lzero.worker.muzero_collector.MuZeroCollector attribute) (lzero.worker.muzero_evaluator.MuZeroEvaluator attribute) _asdict() (lzero.policy.alphazero.AlphaZeroPolicy.collect_function method) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function method) (lzero.policy.alphazero.AlphaZeroPolicy.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.sampled_alphazero.SampledAlphaZeroPolicy.collect_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function method) _calculate_policy_loss_disc() (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _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.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy 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.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.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) _fields (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.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.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute) _forward_collect() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _forward_eval() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _forward_learn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _get_attribute() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _get_batch_size() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _get_n_episode() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _get_n_sample() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _get_simulation_env() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _get_train_sample() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _init_collect() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method)

_init_eval() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _init_learn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _init_multi_gpu_setting() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _is_protocol (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper attribute) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper attribute) _load_state_dict_collect() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _load_state_dict_eval() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _load_state_dict_learn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _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.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.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) _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) _monitor_vars_learn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _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) _policy_value_fn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) _policy_value_func() (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy 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.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _push_game_segment() (lzero.mcts.buffer.game_buffer.GameBuffer method) (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer 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.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.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) _reset_collect() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _reset_eval() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _reset_learn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy 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) _scalar_reward() (lzero.mcts.buffer.game_buffer_muzero.MuZeroGameBuffer method) _set_attribute() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _state_dict_collect() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _state_dict_eval() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method) _state_dict_learn() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy 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)

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)

C

cfg (lzero.policy.alphazero.AlphaZeroPolicy property) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy property) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy property) class_name() (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper class method) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper class 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.gumbel_alphazero.GumbelAlphaZeroPolicy property) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy property) 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.gumbel_alphazero.GumbelAlphaZeroPolicy attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy 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.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.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)

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.gumbel_alphazero.GumbelAlphaZeroPolicy class method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy 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.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method)

E

EfficientZeroMCTSCtree (class in lzero.mcts.tree_search.mcts_ctree) envstep (lzero.worker.muzero_collector.MuZeroCollector property) eval() (lzero.worker.muzero_evaluator.MuZeroEvaluator method) eval_alphazero (class in lzero.entry.eval_alphazero)

eval_mode (lzero.policy.alphazero.AlphaZeroPolicy property) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy property) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy property) eval_muzero (class in lzero.entry.eval_muzero) eval_muzero_with_gym_env (class in lzero.entry.eval_muzero_with_gym_env)

F

forward (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.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.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute)

G

GameBuffer (class in lzero.mcts.buffer.game_buffer) 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.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.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) 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_train_sample (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.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) GumbelMuZeroMCTSCtree (class in lzero.mcts.tree_search.mcts_ctree)

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.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.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)

info (lzero.policy.alphazero.AlphaZeroPolicy.learn_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute)

L

learn_mode (lzero.policy.alphazero.AlphaZeroPolicy property) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy property) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy 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.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.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.config.meta module

M

metadata (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper property) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper property) module lzero.config.meta monitor_vars (lzero.policy.alphazero.AlphaZeroPolicy.learn_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.learn_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.learn_function attribute)

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)

N

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)

P

pad_and_save_last_trajectory() (lzero.worker.muzero_collector.MuZeroCollector method) process_transition (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute)

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) 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) reset (lzero.policy.alphazero.AlphaZeroPolicy.collect_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.eval_function attribute) (lzero.policy.alphazero.AlphaZeroPolicy.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.sampled_alphazero.SampledAlphaZeroPolicy.collect_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.eval_function attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy.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) 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) 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.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.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)

should_eval() (lzero.worker.muzero_evaluator.MuZeroEvaluator method) 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.gumbel_alphazero.GumbelAlphaZeroPolicy.collect_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.eval_function attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy.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) step() (lzero.envs.wrappers.action_discretization_env_wrapper.ActionDiscretizationEnvWrapper method) (lzero.envs.wrappers.lightzero_env_wrapper.LightZeroEnvWrapper method) sync_gradients() (lzero.policy.alphazero.AlphaZeroPolicy method) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy method) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy method)

T

total_field (lzero.policy.alphazero.AlphaZeroPolicy attribute) (lzero.policy.gumbel_alphazero.GumbelAlphaZeroPolicy attribute) (lzero.policy.sampled_alphazero.SampledAlphaZeroPolicy attribute)

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)

U

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)