Index

_

__init__() (agent_base.AgentBase method) (double_q_learning.DoubleQLearning method) (dp_algorithm_base.DPAlgoBase method) (dummy_agent.DummyAgent method) (episodic_sarsa_semi_gradient.EpisodicSarsaSemiGrad method) (extended_kalman_filter.ExtendedKalmanFilter method) (gym_world_wrapper.GymWorldWrapper method) (iterative_policy_evaluation.IterativePolicyEvaluator method) (policy_improvement.PolicyImprovement method) (policy_iteration.PolicyIteration method) (q_learning.QLearning method) (rl_agent_trainer_base.RLAgentTrainerBase method) (rl_serial_algorithm_trainer.RLSerialAgentTrainer method) (sarsa.Sarsa method) (td_algorithm_base.TDAlgoBase method) (td_zero.TDZero method) (value_iteration.ValueIteration method)

_update_q_table() (double_q_learning.DoubleQLearning method) (q_learning.QLearning method)

A

actions_after_episode_ends() (double_q_learning.DoubleQLearning method) (dp_algorithm_base.DPAlgoBase method) (episodic_sarsa_semi_gradient.EpisodicSarsaSemiGrad method) (q_learning.QLearning method) (rl_serial_algorithm_trainer.RLSerialAgentTrainer method) (sarsa.Sarsa method) actions_after_training_ends() (dp_algorithm_base.DPAlgoBase method) (episodic_sarsa_semi_gradient.EpisodicSarsaSemiGrad method) (policy_iteration.PolicyIteration method) (rl_serial_algorithm_trainer.RLSerialAgentTrainer method) (td_algorithm_base.TDAlgoBase method) actions_before_episode_begins() (dp_algorithm_base.DPAlgoBase method) (episodic_sarsa_semi_gradient.EpisodicSarsaSemiGrad method) (rl_serial_algorithm_trainer.RLSerialAgentTrainer method)

actions_before_training_begins() (double_q_learning.DoubleQLearning method) (dp_algorithm_base.DPAlgoBase method) (episodic_sarsa_semi_gradient.EpisodicSarsaSemiGrad method) (iterative_policy_evaluation.IterativePolicyEvaluator method) (policy_iteration.PolicyIteration method) (q_learning.QLearning method) (rl_serial_algorithm_trainer.RLSerialAgentTrainer method) (sarsa.Sarsa method) (td_algorithm_base.TDAlgoBase method) (td_zero.TDZero method) (value_iteration.ValueIteration method) agent_base module AgentBase (class in agent_base)

D

do_on_training_episode() (double_q_learning.DoubleQLearning method) (sarsa.Sarsa method) (td_zero.TDZero method) double_q_learning module DoubleQLearning (class in double_q_learning)

dp_algorithm_base module DPAlgoBase (class in dp_algorithm_base) DPAlgoConfig (class in dp_algorithm_base) dummy_agent module DummyAgent (class in dummy_agent)

E

EKFConfig (class in extended_kalman_filter) episode_info module EpisodeInfo (class in episode_info) episodic_sarsa_semi_gradient module

EpisodicSarsaSemiGrad (class in episodic_sarsa_semi_gradient) extended_kalman_filter module ExtendedKalmanFilter (class in extended_kalman_filter)

G

gamma (dp_algorithm_base.DPAlgoBase property)

GymWorldWrapper (class in gym_world_wrapper)

I

iterative_policy_evaluation module

IterativePolicyEvaluator (class in iterative_policy_evaluation)

M

module agent_base double_q_learning dp_algorithm_base dummy_agent episode_info episodic_sarsa_semi_gradient extended_kalman_filter iterative_policy_evaluation optimizer_type policy_improvement policy_iteration pytorch_optimizer_builder q_learning rl_agent_trainer_base rl_serial_algorithm_trainer sarsa td_algorithm_base td_zero value_iteration world_helpers

N

n_actions (gym_world_wrapper.GymWorldWrapper property) n_actions() (in module world_helpers)

n_states (gym_world_wrapper.GymWorldWrapper property) n_states() (in module world_helpers)

O

on_state() (agent_base.AgentBase method) (dummy_agent.DummyAgent method) on_training_episode() (dp_algorithm_base.DPAlgoBase method) (episodic_sarsa_semi_gradient.EpisodicSarsaSemiGrad method) (iterative_policy_evaluation.IterativePolicyEvaluator method) (policy_improvement.PolicyImprovement method) (policy_iteration.PolicyIteration method) (q_learning.QLearning method) (value_iteration.ValueIteration method)

optimizer_type module OptimizerType (class in optimizer_type)

P

play() (agent_base.AgentBase method) (dummy_agent.DummyAgent method) policy (policy_iteration.PolicyIteration property) policy_improvement module policy_iteration module

PolicyImprovement (class in policy_improvement) PolicyIteration (class in policy_iteration) pytorch_optimizer_builder module pytorch_optimizer_builder() (in module pytorch_optimizer_builder)

Q

q_learning module

QLearning (class in q_learning)

R

render() (gym_world_wrapper.GymWorldWrapper method) reset() (gym_world_wrapper.GymWorldWrapper method) (in module world_helpers) rl_agent_trainer_base module

rl_serial_algorithm_trainer module RLAgentTrainerBase (class in rl_agent_trainer_base) RLAgentTrainerConfig (class in rl_agent_trainer_base) RLSerialAgentTrainer (class in rl_serial_algorithm_trainer) RLSerialTrainerConfig (class in rl_serial_algorithm_trainer)

S

sample_action() (gym_world_wrapper.GymWorldWrapper method) sarsa module

Sarsa (class in sarsa) SemiGradSARSAConfig (class in episodic_sarsa_semi_gradient) step() (gym_world_wrapper.GymWorldWrapper method) (in module world_helpers)

T

td_algorithm_base module td_zero module

TDAlgoBase (class in td_algorithm_base) TDAlgoConfig (class in td_algorithm_base) TDZero (class in td_zero) train() (rl_agent_trainer_base.RLAgentTrainerBase method) (rl_serial_algorithm_trainer.RLSerialAgentTrainer method)

U

update_q_table() (sarsa.Sarsa method)

update_weights() (episodic_sarsa_semi_gradient.EpisodicSarsaSemiGrad method)

V

value_iteration module

ValueIteration (class in value_iteration)

W

world_helpers module