• Agent
  • AlphaZeroAgent
    • AlphaZeroAgent.__init__()
    • AlphaZeroAgent.batch_evaluate()
    • AlphaZeroAgent.best
    • AlphaZeroAgent.deploy()
    • AlphaZeroAgent.supported_env_list
    • AlphaZeroAgent.train()
  • MuZeroAgent
    • MuZeroAgent.__init__()
    • MuZeroAgent.batch_evaluate()
    • MuZeroAgent.best
    • MuZeroAgent.deploy()
    • MuZeroAgent.supported_env_list
    • MuZeroAgent.train()
  • EfficientZeroAgent
    • EfficientZeroAgent.__init__()
    • EfficientZeroAgent.batch_evaluate()
    • EfficientZeroAgent.best
    • EfficientZeroAgent.deploy()
    • EfficientZeroAgent.supported_env_list
    • EfficientZeroAgent.train()
  • GumbelMuZeroAgent
    • GumbelMuZeroAgent.__init__()
    • GumbelMuZeroAgent.batch_evaluate()
    • GumbelMuZeroAgent.best
    • GumbelMuZeroAgent.deploy()
    • GumbelMuZeroAgent.supported_env_list
    • GumbelMuZeroAgent.train()
  • SampledEfficientZeroAgent
    • SampledEfficientZeroAgent.__init__()
    • SampledEfficientZeroAgent.batch_evaluate()
    • SampledEfficientZeroAgent.best
    • SampledEfficientZeroAgent.deploy()
    • SampledEfficientZeroAgent.supported_env_list
    • SampledEfficientZeroAgent.train()
  • SampledAlphaZeroAgent
    • SampledAlphaZeroAgent.__init__()
    • SampledAlphaZeroAgent.batch_evaluate()
    • SampledAlphaZeroAgent.best
    • SampledAlphaZeroAgent.deploy()
    • SampledAlphaZeroAgent.supported_env_list
    • SampledAlphaZeroAgent.train()
• Config
  • lzero.config.meta
    • __TITLE__
    • __VERSION__
    • __DESCRIPTION__
    • __AUTHOR__
    • __AUTHOR_EMAIL__
• Entry
  • train_alphazero
    • train_alphazero.__init__()
  • eval_alphazero
    • eval_alphazero.__init__()
  • train_muzero
    • train_muzero.__init__()
  • eval_muzero
    • eval_muzero.__init__()
  • train_muzero_with_gym_env
    • train_muzero_with_gym_env.__init__()
  • eval_muzero_with_gym_env
    • eval_muzero_with_gym_env.__init__()
  • train_muzero_with_reward_model
    • train_muzero_with_reward_model.__init__()
• Envs
  • LightZeroEnvWrapper
    • LightZeroEnvWrapper.__init__()
    • LightZeroEnvWrapper._is_protocol
    • LightZeroEnvWrapper._np_random
    • LightZeroEnvWrapper.action_space
    • LightZeroEnvWrapper.class_name()
    • LightZeroEnvWrapper.close()
    • LightZeroEnvWrapper.metadata
    • LightZeroEnvWrapper.np_random
    • LightZeroEnvWrapper.observation_space
    • LightZeroEnvWrapper.render()
    • LightZeroEnvWrapper.render_mode
    • LightZeroEnvWrapper.reset()
    • LightZeroEnvWrapper.reward_range
    • LightZeroEnvWrapper.seed()
    • LightZeroEnvWrapper.spec
    • LightZeroEnvWrapper.step()
    • LightZeroEnvWrapper.unwrapped
  • ActionDiscretizationEnvWrapper
    • ActionDiscretizationEnvWrapper.__init__()
    • ActionDiscretizationEnvWrapper._is_protocol
    • ActionDiscretizationEnvWrapper._np_random
    • ActionDiscretizationEnvWrapper.action_space
    • ActionDiscretizationEnvWrapper.class_name()
    • ActionDiscretizationEnvWrapper.close()
    • ActionDiscretizationEnvWrapper.metadata
    • ActionDiscretizationEnvWrapper.np_random
    • ActionDiscretizationEnvWrapper.observation_space
    • ActionDiscretizationEnvWrapper.render()
    • ActionDiscretizationEnvWrapper.render_mode
    • ActionDiscretizationEnvWrapper.reset()
    • ActionDiscretizationEnvWrapper.reward_range
    • ActionDiscretizationEnvWrapper.seed()
    • ActionDiscretizationEnvWrapper.spec
    • ActionDiscretizationEnvWrapper.step()
    • ActionDiscretizationEnvWrapper.unwrapped
• MCTS
  • Buffer
    • GameBuffer
    • MuZeroBuffer
    • EfficientZeroBuffer
  • Tree Search
    • MuZeroMCTSCtree
    • EfficientZeroMCTSCtree
    • GumbelMuZeroMCTSCtree
• Model
  • Common
    • SimNorm
    • FeatureAndGradientHook
    • DownSample
    • RepresentationNetworkUniZero
    • RepresentationNetwork
    • RepresentationNetworkMLP
    • LatentDecoder
    • LatentEncoderForMemoryEnv
    • LatentDecoderForMemoryEnv
    • VectorDecoderForMemoryEnv
    • PredictionNetwork
    • PredictionNetworkMLP
    • PredictionHiddenNetwork
  • MuZeroModel
    • MuZeroModel
    • DynamicsNetwork
  • MuZeroModelMLP
    • MuZeroModelMLP
    • DynamicsNetwork
  • EfficientZeroModel
    • DynamicsNetwork
  • EfficientZeroModelMLP
    • DynamicsNetworkMLP
  • AlphaZeroModel
    • AlphaZeroModel
    • PredictionNetwork
  • SampledEfficientZeroModel
    • PredictionNetwork
  • SampledEfficientZeroModelMLP
    • PredictionNetworkMLP
  • StochasticMuZeroModel
    • StochasticMuZeroModel
    • DynamicsNetwork
    • AfterstatePredictionNetwork
    • ChanceEncoderBackbone
    • ChanceEncoderBackboneMLP
    • ChanceEncoder
    • StraightThroughEstimator
    • OnehotArgmax
  • StochasticMuZeroModelMLP
    • StochasticMuZeroModelMLP
• Policy
  • AlphaZeroPolicy
    • AlphaZeroPolicy
  • MuZeroPolicy
    • MuZeroPolicy
  • EfficientZeroPolicy
    • EfficientZeroPolicy
  • Gumbel AlphaZeroPolicy
    • GumbelAlphaZeroPolicy
  • Gumbel MuZeroPolicy
    • GumbelMuZeroPolicy
  • Sampled AlphaZeroPolicy
    • SampledAlphaZeroPolicy
  • Sampled MuZeroPolicy
    • SampledMuZeroPolicy
  • Sampled EfficientZeroPolicy
    • SampledEfficientZeroPolicy
  • Stochastic MuZeroPolicy
    • StochasticMuZeroPolicy
  • UniZeroPolicy
    • UniZeroPolicy
• Worker
  • MuZeroCollector
    • MuZeroCollector
  • MuZeroEvaluator
    • MuZeroEvaluator