Index

A

actions (rlforge.environments.short_corridor.ShortCorridor property)

append() (rlforge.agents.semi_gradient.dqn_pytorch.ReplayBuffer method) argmax (class in rlforge.utils)

B

BanditAgent (class in rlforge.agents.bandit)

Bandits (class in rlforge.environments.bandits) BaseAgent (class in rlforge.agents.base_agent)

C

clear() (rlforge.agents.semi_gradient.dqn_pytorch.ReplayBuffer method)

close() (rlforge.environments.short_corridor.ShortCorridor method)

D

DDPGAgent (class in rlforge.agents.policy_gradient.ddpg) DQNAgent (class in rlforge.agents.semi_gradient.dqn)

DQNTorchAgent (class in rlforge.agents.semi_gradient.dqn_pytorch) DynaMaze (class in rlforge.environments.dyna_maze)

E

end() (rlforge.agents.base_agent.BaseAgent method) (rlforge.agents.policy_gradient.ddpg.DDPGAgent method) (rlforge.agents.policy_gradient.gaussian_actor_critic.GaussianActorCriticAgent method) (rlforge.agents.policy_gradient.ppo_continuous.PPOContinuous method) (rlforge.agents.policy_gradient.ppo_discrete.PPODiscrete method) (rlforge.agents.policy_gradient.reinforce.REINFORCEAgent method) (rlforge.agents.policy_gradient.sac.SACAgent method) (rlforge.agents.policy_gradient.softmax_actor_critic.SoftmaxActorCriticAgent method) (rlforge.agents.policy_gradient.td3.TD3Agent method) (rlforge.agents.semi_gradient.dqn.DQNAgent method) (rlforge.agents.semi_gradient.dqn_pytorch.DQNTorchAgent method) (rlforge.agents.semi_gradient.linear_sg_agent.LinearQAgent method) (rlforge.agents.tabular.expected_sarsa.ExpectedSarsaAgent method) (rlforge.agents.tabular.planning_agent.PlanningAgent method) (rlforge.agents.tabular.q_agent.QAgent method) (rlforge.agents.tabular.sarsa.SarsaAgent method)

end_batch() (rlforge.agents.policy_gradient.ddpg.DDPGAgent method) (rlforge.agents.policy_gradient.ppo_continuous.PPOContinuous method) (rlforge.agents.policy_gradient.ppo_discrete.PPODiscrete method) (rlforge.agents.policy_gradient.sac.SACAgent method) (rlforge.agents.policy_gradient.td3.TD3Agent method) (rlforge.agents.semi_gradient.dqn_pytorch.DQNTorchAgent method) epsilonGreedy (class in rlforge.policies) ExpectedSarsaAgent (class in rlforge.agents.tabular.expected_sarsa) ExperienceBuffer (class in rlforge.utils) ExperimentRunner (class in rlforge.experiments.experiment_runner)

G

gaussian (class in rlforge.policies) GaussianActorCriticAgent (class in rlforge.agents.policy_gradient.gaussian_actor_critic) get_td_error() (rlforge.agents.policy_gradient.gaussian_actor_critic.GaussianActorCriticAgent method) (rlforge.agents.policy_gradient.softmax_actor_critic.SoftmaxActorCriticAgent method) (rlforge.agents.semi_gradient.dqn.DQNAgent method) (rlforge.agents.semi_gradient.linear_sg_agent.LinearQAgent method)

L

LinearQAgent (class in rlforge.agents.semi_gradient.linear_sg_agent) load() (rlforge.agents.policy_gradient.ddpg.DDPGAgent method) (rlforge.agents.policy_gradient.ppo_continuous.PPOContinuous method) (rlforge.agents.policy_gradient.ppo_discrete.PPODiscrete method) (rlforge.agents.policy_gradient.sac.SACAgent method) (rlforge.agents.policy_gradient.td3.TD3Agent method) (rlforge.agents.semi_gradient.dqn_pytorch.DQNTorchAgent method)

load_results() (rlforge.experiments.experiment_runner.ExperimentRunner method)

M

MecanumCar (class in rlforge.environments.mecanum_car) module rlforge.agents.bandit rlforge.agents.base_agent rlforge.agents.policy_gradient.ddpg rlforge.agents.policy_gradient.gaussian_actor_critic rlforge.agents.policy_gradient.ppo_continuous rlforge.agents.policy_gradient.ppo_discrete rlforge.agents.policy_gradient.reinforce rlforge.agents.policy_gradient.sac rlforge.agents.policy_gradient.softmax_actor_critic rlforge.agents.policy_gradient.td3 rlforge.agents.semi_gradient.dqn rlforge.agents.semi_gradient.dqn_pytorch rlforge.agents.semi_gradient.linear_sg_agent rlforge.agents.tabular.expected_sarsa rlforge.agents.tabular.planning_agent rlforge.agents.tabular.q_agent rlforge.agents.tabular.sarsa rlforge.environments.bandits rlforge.environments.dyna_maze rlforge.environments.mecanum_car rlforge.environments.obstacle_avoidance rlforge.environments.pendulum rlforge.environments.short_corridor rlforge.environments.shortcut_maze rlforge.environments.trajectory_tracking rlforge.experiments.experiment_runner

O

ObstacleAvoidance (class in rlforge.environments.obstacle_avoidance)

optimal_action() (rlforge.environments.bandits.Bandits method)

P

Pendulum (class in rlforge.environments.pendulum) planning_step() (rlforge.agents.tabular.expected_sarsa.ExpectedSarsaAgent method) (rlforge.agents.tabular.planning_agent.PlanningAgent method) (rlforge.agents.tabular.q_agent.QAgent method)

PlanningAgent (class in rlforge.agents.tabular.planning_agent) plot_results() (rlforge.experiments.experiment_runner.ExperimentRunner method) PPOContinuous (class in rlforge.agents.policy_gradient.ppo_continuous) PPODiscrete (class in rlforge.agents.policy_gradient.ppo_discrete) pull() (rlforge.environments.bandits.Bandits method)

Q

QAgent (class in rlforge.agents.tabular.q_agent)

R

REINFORCEAgent (class in rlforge.agents.policy_gradient.reinforce) render() (rlforge.environments.short_corridor.ShortCorridor method) ReplayBuffer (class in rlforge.agents.semi_gradient.dqn_pytorch) reset() (rlforge.agents.base_agent.BaseAgent method) (rlforge.agents.policy_gradient.ddpg.DDPGAgent method) (rlforge.agents.policy_gradient.gaussian_actor_critic.GaussianActorCriticAgent method) (rlforge.agents.policy_gradient.ppo_continuous.PPOContinuous method) (rlforge.agents.policy_gradient.ppo_discrete.PPODiscrete method) (rlforge.agents.policy_gradient.reinforce.REINFORCEAgent method) (rlforge.agents.policy_gradient.sac.SACAgent method) (rlforge.agents.policy_gradient.softmax_actor_critic.SoftmaxActorCriticAgent method) (rlforge.agents.policy_gradient.td3.TD3Agent method) (rlforge.agents.semi_gradient.dqn.DQNAgent method) (rlforge.agents.semi_gradient.dqn_pytorch.DQNTorchAgent method) (rlforge.agents.semi_gradient.linear_sg_agent.LinearQAgent method) (rlforge.agents.tabular.expected_sarsa.ExpectedSarsaAgent method) (rlforge.agents.tabular.planning_agent.PlanningAgent method) (rlforge.agents.tabular.q_agent.QAgent method) (rlforge.agents.tabular.sarsa.SarsaAgent method) (rlforge.environments.dyna_maze.DynaMaze method) (rlforge.environments.mecanum_car.MecanumCar method) (rlforge.environments.obstacle_avoidance.ObstacleAvoidance method) (rlforge.environments.pendulum.Pendulum method) (rlforge.environments.short_corridor.ShortCorridor method) (rlforge.environments.shortcut_maze.ShortcutMaze method) (rlforge.environments.trajectory_tracking.TrajectoryTracking method) reset_nets_and_opts() (rlforge.agents.policy_gradient.ddpg.DDPGAgent method) (rlforge.agents.policy_gradient.sac.SACAgent method) (rlforge.agents.policy_gradient.td3.TD3Agent method) reset_networks() (rlforge.agents.semi_gradient.dqn_pytorch.DQNTorchAgent method) rlforge.agents.bandit module rlforge.agents.base_agent module rlforge.agents.policy_gradient.ddpg module rlforge.agents.policy_gradient.gaussian_actor_critic module rlforge.agents.policy_gradient.ppo_continuous module rlforge.agents.policy_gradient.ppo_discrete module

rlforge.agents.policy_gradient.reinforce module rlforge.agents.policy_gradient.sac module rlforge.agents.policy_gradient.softmax_actor_critic module rlforge.agents.policy_gradient.td3 module rlforge.agents.semi_gradient.dqn module rlforge.agents.semi_gradient.dqn_pytorch module rlforge.agents.semi_gradient.linear_sg_agent module rlforge.agents.tabular.expected_sarsa module rlforge.agents.tabular.planning_agent module rlforge.agents.tabular.q_agent module rlforge.agents.tabular.sarsa module rlforge.environments.bandits module rlforge.environments.dyna_maze module rlforge.environments.mecanum_car module rlforge.environments.obstacle_avoidance module rlforge.environments.pendulum module rlforge.environments.short_corridor module rlforge.environments.shortcut_maze module rlforge.environments.trajectory_tracking module rlforge.experiments.experiment_runner module run_continuous() (rlforge.experiments.experiment_runner.ExperimentRunner method) run_episodic() (rlforge.experiments.experiment_runner.ExperimentRunner method) run_episodic_batch() (rlforge.experiments.experiment_runner.ExperimentRunner method)

S

SACAgent (class in rlforge.agents.policy_gradient.sac) sample() (rlforge.agents.semi_gradient.dqn_pytorch.ReplayBuffer method) SarsaAgent (class in rlforge.agents.tabular.sarsa) save() (rlforge.agents.policy_gradient.ddpg.DDPGAgent method) (rlforge.agents.policy_gradient.ppo_continuous.PPOContinuous method) (rlforge.agents.policy_gradient.ppo_discrete.PPODiscrete method) (rlforge.agents.policy_gradient.sac.SACAgent method) (rlforge.agents.policy_gradient.td3.TD3Agent method) (rlforge.agents.semi_gradient.dqn_pytorch.DQNTorchAgent method) save_results() (rlforge.experiments.experiment_runner.ExperimentRunner method) select_action() (rlforge.agents.bandit.BanditAgent method) (rlforge.agents.base_agent.BaseAgent method) (rlforge.agents.policy_gradient.gaussian_actor_critic.GaussianActorCriticAgent method) (rlforge.agents.policy_gradient.softmax_actor_critic.SoftmaxActorCriticAgent method) (rlforge.agents.semi_gradient.dqn.DQNAgent method) (rlforge.agents.semi_gradient.linear_sg_agent.LinearQAgent method) (rlforge.agents.tabular.expected_sarsa.ExpectedSarsaAgent method) (rlforge.agents.tabular.planning_agent.PlanningAgent method) (rlforge.agents.tabular.q_agent.QAgent method) (rlforge.agents.tabular.sarsa.SarsaAgent method) ShortCorridor (class in rlforge.environments.short_corridor) ShortcutMaze (class in rlforge.environments.shortcut_maze) softmax (class in rlforge.policies) softmax() (in module rlforge.agents.semi_gradient.dqn_pytorch) SoftmaxActorCriticAgent (class in rlforge.agents.policy_gradient.softmax_actor_critic) start() (rlforge.agents.base_agent.BaseAgent method) (rlforge.agents.policy_gradient.ddpg.DDPGAgent method) (rlforge.agents.policy_gradient.gaussian_actor_critic.GaussianActorCriticAgent method) (rlforge.agents.policy_gradient.ppo_continuous.PPOContinuous method) (rlforge.agents.policy_gradient.ppo_discrete.PPODiscrete method) (rlforge.agents.policy_gradient.reinforce.REINFORCEAgent method) (rlforge.agents.policy_gradient.sac.SACAgent method) (rlforge.agents.policy_gradient.softmax_actor_critic.SoftmaxActorCriticAgent method) (rlforge.agents.policy_gradient.td3.TD3Agent method) (rlforge.agents.semi_gradient.dqn.DQNAgent method) (rlforge.agents.semi_gradient.dqn_pytorch.DQNTorchAgent method) (rlforge.agents.semi_gradient.linear_sg_agent.LinearQAgent method) (rlforge.agents.tabular.expected_sarsa.ExpectedSarsaAgent method) (rlforge.agents.tabular.planning_agent.PlanningAgent method) (rlforge.agents.tabular.q_agent.QAgent method) (rlforge.agents.tabular.sarsa.SarsaAgent method)

start_batch() (rlforge.agents.policy_gradient.ddpg.DDPGAgent method) (rlforge.agents.policy_gradient.ppo_continuous.PPOContinuous method) (rlforge.agents.policy_gradient.ppo_discrete.PPODiscrete method) (rlforge.agents.policy_gradient.sac.SACAgent method) (rlforge.agents.policy_gradient.td3.TD3Agent method) (rlforge.agents.semi_gradient.dqn_pytorch.DQNTorchAgent method) step() (rlforge.agents.base_agent.BaseAgent method) (rlforge.agents.policy_gradient.ddpg.DDPGAgent method) (rlforge.agents.policy_gradient.gaussian_actor_critic.GaussianActorCriticAgent method) (rlforge.agents.policy_gradient.ppo_continuous.PPOContinuous method) (rlforge.agents.policy_gradient.ppo_discrete.PPODiscrete method) (rlforge.agents.policy_gradient.reinforce.REINFORCEAgent method) (rlforge.agents.policy_gradient.sac.SACAgent method) (rlforge.agents.policy_gradient.softmax_actor_critic.SoftmaxActorCriticAgent method) (rlforge.agents.policy_gradient.td3.TD3Agent method) (rlforge.agents.semi_gradient.dqn.DQNAgent method) (rlforge.agents.semi_gradient.dqn_pytorch.DQNTorchAgent method) (rlforge.agents.semi_gradient.linear_sg_agent.LinearQAgent method) (rlforge.agents.tabular.expected_sarsa.ExpectedSarsaAgent method) (rlforge.agents.tabular.planning_agent.PlanningAgent method) (rlforge.agents.tabular.q_agent.QAgent method) (rlforge.agents.tabular.sarsa.SarsaAgent method) (rlforge.environments.dyna_maze.DynaMaze method) (rlforge.environments.mecanum_car.MecanumCar method) (rlforge.environments.obstacle_avoidance.ObstacleAvoidance method) (rlforge.environments.pendulum.Pendulum method) (rlforge.environments.short_corridor.ShortCorridor method) (rlforge.environments.shortcut_maze.ShortcutMaze method) (rlforge.environments.trajectory_tracking.TrajectoryTracking method) step_batch() (rlforge.agents.policy_gradient.ddpg.DDPGAgent method) (rlforge.agents.policy_gradient.ppo_continuous.PPOContinuous method) (rlforge.agents.policy_gradient.ppo_discrete.PPODiscrete method) (rlforge.agents.policy_gradient.sac.SACAgent method) (rlforge.agents.policy_gradient.td3.TD3Agent method) (rlforge.agents.semi_gradient.dqn_pytorch.DQNTorchAgent method) summary() (rlforge.experiments.experiment_runner.ExperimentRunner method)

T

TD3Agent (class in rlforge.agents.policy_gradient.td3)

TrajectoryTracking (class in rlforge.environments.trajectory_tracking)

U

update() (rlforge.agents.bandit.BanditAgent method) update_model() (rlforge.agents.tabular.expected_sarsa.ExpectedSarsaAgent method) (rlforge.agents.tabular.planning_agent.PlanningAgent method) (rlforge.agents.tabular.q_agent.QAgent method)

update_q_values() (rlforge.agents.tabular.expected_sarsa.ExpectedSarsaAgent method) (rlforge.agents.tabular.planning_agent.PlanningAgent method) (rlforge.agents.tabular.q_agent.QAgent method)