Index

_

__call__() (epsilon_greedy_policy.EpsilonGreedyPolicy method) __contains__() (state.State method) __getitem__() (replay_buffer.ReplayBuffer method) (serial_hierarchy.SerialHierarchy method) (state.State method) __init__() (a2c.A2C method) (a2c_networks.A2CNetSimpleLinear method) (actions.ActionBase method) (actions.ActionIdentity method) (actions.ActionNumericBinGeneralize method) (actions.ActionNumericStepGeneralize method) (actions.ActionRestore method) (actions.ActionStringGeneralize method) (actions.ActionSuppress method) (actions.ActionTransform method) (epsilon_greedy_policy.EpsilonGreedyPolicy method) (epsilon_greedy_q_estimator.EpsilonGreedyQEstimator method) (exceptions.Error method) (exceptions.IncompatibleVectorSizesException method) (exceptions.InvalidDataTypeException method) (exceptions.InvalidFileFormat method) (exceptions.InvalidParamValue method) (exceptions.InvalidSchemaException method) (exceptions.InvalidStateException method) (iteration_control.IterationControl method) (mixins.WithHierarchyTable method) (mixins.WithMaxActionMixin method) (mixins.WithQTableMixin method) (mixins.WithQTableMixinBase method) (multiprocess_env.MultiprocessEnv method) (processes_manager.TorchProcsHandler method) (pytorch_trainer.PyTorchTrainer method) (q_learning.QLearning method) (replay_buffer.ReplayBuffer method) (reward_manager.RewardManager method) (semi_gradient_sarsa.SemiGradSARSA method) (serial_hierarchy.SerialHierarchy method) (state.State method) (state.StateIterator method) (trainer.Trainer method)

__len__() (multiprocess_env.MultiprocessEnv method) (processes_manager.TorchProcsHandler method) (replay_buffer.ReplayBuffer method) (serial_hierarchy.SerialHierarchy method) (state.StateIterator method) __setitem__() (serial_hierarchy.SerialHierarchy method) __str__() (epsilon_greedy_policy.EpsilonGreedyPolicy method) (exceptions.Error method) (exceptions.IncompatibleVectorSizesException method) (exceptions.InvalidDataTypeException method) (exceptions.InvalidFileFormat method) (exceptions.InvalidParamValue method) (exceptions.InvalidSchemaException method) (exceptions.InvalidStateException method) _ActResult (class in a2c) _broadcast_msg() (multiprocess_env.MultiprocessEnv method) _do_train() (a2c.A2C method) (q_learning.QLearning method) (semi_gradient_sarsa.SemiGradSARSA method) _init() (semi_gradient_sarsa.SemiGradSARSA method) _send_msg() (multiprocess_env.MultiprocessEnv method) _update_q_table() (q_learning.QLearning method) _validate() (semi_gradient_sarsa.SemiGradSARSA method) _weights_update() (semi_gradient_sarsa.SemiGradSARSA method) _weights_update_episode_done() (semi_gradient_sarsa.SemiGradSARSA method)

A

a2c module A2C (class in a2c) a2c_networks module A2CConfig (class in a2c) A2CNetSimpleLinear (class in a2c_networks) act() (actions.ActionBase method) (actions.ActionIdentity method) (actions.ActionNumericBinGeneralize method) (actions.ActionNumericStepGeneralize method) (actions.ActionRestore method) (actions.ActionStringGeneralize method) (actions.ActionSuppress method) (actions.ActionTransform method) action_space module ActionBase (class in actions) ActionIdentity (class in actions) ActionNumericBinGeneralize (class in actions) ActionNumericStepGeneralize (class in actions) ActionRestore (class in actions) actions module

actions_after_episode() (epsilon_greedy_policy.EpsilonGreedyPolicy method) actions_after_episode_ends() (pytorch_trainer.PyTorchTrainer method) (q_learning.QLearning method) (semi_gradient_sarsa.SemiGradSARSA method) (trainer.Trainer method) actions_before_episode_begins() (pytorch_trainer.PyTorchTrainer method) (semi_gradient_sarsa.SemiGradSARSA method) (trainer.Trainer method) actions_before_training() (pytorch_trainer.PyTorchTrainer method) (q_learning.QLearning method) (semi_gradient_sarsa.SemiGradSARSA method) (trainer.Trainer method) ActionSpace (class in action_space) ActionStringGeneralize (class in actions) ActionSuppress (class in actions) ActionTransform (class in actions) ActionType (class in actions) add() (actions.ActionStringGeneralize method) (replay_buffer.ReplayBuffer method) add_hierarchy() (mixins.WithHierarchyTable method) at (state.StateIterator property) avg_distortion() (pytorch_trainer.PyTorchTrainer method) (trainer.Trainer method) avg_rewards() (pytorch_trainer.PyTorchTrainer method) (trainer.Trainer method)

C

calculate_discounted_returns() (in module a2c) column_type module

ColumnType (class in column_type) copy_time_step() (in module time_step) create_discounts_array() (in module a2c)

D

discrete_state_environment module

E

episode_info module EpisodeInfo (class in episode_info) epsilon_greedy_policy module epsilon_greedy_q_estimator module

EpsilonDecayOption (class in epsilon_greedy_policy) EpsilonGreedyConfig (class in epsilon_greedy_policy) EpsilonGreedyPolicy (class in epsilon_greedy_policy) EpsilonGreedyQEstimator (class in epsilon_greedy_q_estimator) EpsilonGreedyQEstimatorConfig (class in epsilon_greedy_q_estimator) Error (class in exceptions) exceptions module

F

finished (state.StateIterator property) finished() (mixins.WithHierarchyTable method) forward() (a2c_networks.A2CNetSimpleLinear method)

from_config() (epsilon_greedy_policy.EpsilonGreedyPolicy class method) from_path() (a2c.A2C class method) function_wraps module

G

get_item_as_torch_tensor() (replay_buffer.ReplayBuffer method)

get_reward_for_state() (reward_manager.RewardManager method)

I

IncompatibleVectorSizesException (class in exceptions) initialize() (epsilon_greedy_q_estimator.EpsilonGreedyQEstimator method) InvalidDataTypeException (class in exceptions) InvalidFileFormat (class in exceptions) InvalidParamValue (class in exceptions)

InvalidSchemaException (class in exceptions) InvalidStateException (class in exceptions) iteration_control module IterationControl (class in iteration_control)

L

loss_functions module

M

make() (multiprocess_env.MultiprocessEnv method) max_action() (mixins.WithMaxActionMixin method) mixins module module a2c a2c_networks action_space actions column_type discrete_state_environment episode_info epsilon_greedy_policy epsilon_greedy_q_estimator exceptions function_wraps iteration_control loss_functions mixins multiprocess_env numeric_distance_type optimizer_type processes_manager pytorch_optimizer_builder pytorch_optimizer_config pytorch_trainer q_learning replay_buffer reward_manager semi_gradient_sarsa serial_hierarchy state time_step trainer

mse() (in module loss_functions) multiprocess_env module MultiprocessEnv (class in multiprocess_env)

N

numeric_distance_type module

NumericDistanceType (class in numeric_distance_type)

O

on_episode() (a2c.A2C method) (q_learning.QLearning method) (semi_gradient_sarsa.SemiGradSARSA method) on_state() (epsilon_greedy_policy.EpsilonGreedyPolicy method) (epsilon_greedy_q_estimator.EpsilonGreedyQEstimator method)

optimizer_type module OptimizerType (class in optimizer_type)

P

parameters() (a2c.A2C method) play() (q_learning.QLearning method) (semi_gradient_sarsa.SemiGradSARSA method) processes_manager module pytorch_optimizer_builder module

pytorch_optimizer_builder() (in module pytorch_optimizer_builder) pytorch_optimizer_config module pytorch_trainer module PyTorchOptimizerConfig (class in pytorch_optimizer_config) PyTorchTrainer (class in pytorch_trainer) PyTorchTrainerConfig (class in pytorch_trainer)

Q

q_hat_value() (epsilon_greedy_q_estimator.EpsilonGreedyQEstimator method) q_learning module

QLearnConfig (class in q_learning) QLearning (class in q_learning)

R

reinitialize() (replay_buffer.ReplayBuffer method) replay_buffer module ReplayBuffer (class in replay_buffer)

reset_iterators() (mixins.WithHierarchyTable method) reward_manager module RewardManager (class in reward_manager)

S

sample() (replay_buffer.ReplayBuffer method) semi_gradient_sarsa module SemiGradSARSA (class in semi_gradient_sarsa) SemiGradSARSAConfig (class in semi_gradient_sarsa) serial_hierarchy module

SerialHierarchy (class in serial_hierarchy) state module State (class in state) StateIterator (class in state) StepType (class in time_step)

T

time_func() (in module function_wraps) time_step module TimeStep (class in time_step) TorchProcsHandler (class in processes_manager)

train() (trainer.Trainer method) trainer module Trainer (class in trainer) TrainerConfig (class in trainer)

W

WithEstimatorMixin (class in mixins) WithHierarchyTable (class in mixins) WithMaxActionMixin (class in mixins)

WithQTableMixin (class in mixins) WithQTableMixinBase (class in mixins) work() (multiprocess_env.MultiprocessEnv method) worker() (in module pytorch_trainer)