latest
User Guide
Installation
About
Tutorials
API
Agents
Environments
Core
Utilities
Trainers
Common
GenRL
Docs
»
Index
Edit on GitHub
Index
A
|
B
|
C
|
D
|
E
|
F
|
G
|
H
|
I
|
L
|
M
|
N
|
O
|
P
|
Q
|
R
|
S
|
T
|
U
|
V
|
W
A
a (genrl.agents.bandits.multiarmed.bayesian.BayesianUCBMABAgent attribute)
(genrl.agents.bandits.multiarmed.thompson.ThompsonSamplingMABAgent attribute)
A2C (class in genrl.agents.deep.a2c.a2c)
action() (genrl.environments.action_wrappers.ClipAction method)
(genrl.environments.action_wrappers.RescaleAction method)
action_dim (genrl.core.actor_critic.MlpActorCritic attribute)
(genrl.core.actor_critic.MlpSharedActorCritic attribute)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic attribute)
(genrl.core.actor_critic.MlpSingleActorTwoCritic attribute)
(genrl.core.values.CnnCategoricalValue attribute)
(genrl.core.values.CnnDuelingValue attribute)
(genrl.core.values.CnnNoisyValue attribute)
(genrl.core.values.MlpCategoricalValue attribute)
(genrl.core.values.MlpDuelingValue attribute)
action_hist (genrl.agents.bandits.multiarmed.base.MABAgent attribute)
action_shape (genrl.environments.gym_wrapper.GymWrapper attribute)
(genrl.environments.vec_env.vector_envs.VecEnv attribute)
action_spaces (genrl.environments.vec_env.vector_envs.VecEnv attribute)
ActionNoise (class in genrl.core.noise)
actions (genrl.core.buffers.PrioritizedReplayBufferSamples attribute)
(genrl.core.buffers.ReplayBufferSamples attribute)
(genrl.core.rollout_storage.ReplayBufferSamples attribute)
(genrl.core.rollout_storage.RolloutBufferSamples attribute)
activation (genrl.core.actor_critic.MlpActorCritic attribute)
(genrl.core.actor_critic.MlpSharedActorCritic attribute)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic attribute)
(genrl.core.actor_critic.MlpSingleActorTwoCritic attribute)
add() (genrl.agents.bandits.contextual.common.transition.TransitionDB method)
(genrl.core.rollout_storage.BaseBuffer method)
(genrl.core.rollout_storage.RolloutBuffer method)
(genrl.utils.models.TabularModel method)
advantages (genrl.core.rollout_storage.RolloutBufferSamples attribute)
agent (in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
alpha (genrl.agents.bandits.multiarmed.gradient.GradientMABAgent attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
AtariEnv() (in module genrl.environments.suite)
AtariPreprocessing (class in genrl.environments.atari_preprocessing)
AtariTimeLimit (class in genrl.environments.time_limit)
B
b (genrl.agents.bandits.multiarmed.bayesian.BayesianUCBMABAgent attribute)
(genrl.agents.bandits.multiarmed.thompson.ThompsonSamplingMABAgent attribute)
bandit (genrl.agents.bandits.contextual.base.DCBAgent attribute)
BaseActorCritic (class in genrl.core.base)
BaseAgent (class in genrl.agents.deep.base.base)
BaseBuffer (class in genrl.core.rollout_storage)
BasePolicy (class in genrl.core.base)
BaseValue (class in genrl.core.base)
BaseWrapper (class in genrl.environments.base_wrapper)
batch_size (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.base.BaseAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
(genrl.environments.base_wrapper.BaseWrapper attribute)
BayesianLinear (class in genrl.agents.bandits.contextual.common.bayesian)
BayesianNNBanditModel (class in genrl.agents.bandits.contextual.common.bayesian)
BayesianUCBMABAgent (class in genrl.agents.bandits.multiarmed.bayesian)
BernoulliMAB (class in genrl.agents.bandits.multiarmed.bernoulli_mab)
beta (genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
BootstrapNeuralAgent (class in genrl.agents.bandits.contextual.bootstrap_neural)
buffer (in module genrl.trainers.OffPolicyTrainer)
buffer_type (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
C
calculate_epsilon_by_frame() (genrl.agents.deep.dqn.base.DQN method)
categorical_greedy_action() (in module genrl.agents.deep.dqn.utils)
categorical_q_loss() (in module genrl.agents.deep.dqn.utils)
categorical_q_target() (in module genrl.agents.deep.dqn.utils)
categorical_q_values() (in module genrl.agents.deep.dqn.utils)
CategoricalDQN (class in genrl.agents.deep.dqn.categorical)
clip_param (genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
ClipAction (class in genrl.environments.action_wrappers)
close() (genrl.environments.base_wrapper.BaseWrapper method)
(genrl.environments.gym_wrapper.GymWrapper method)
(genrl.environments.vec_env.normalize.VecNormalize method)
(genrl.environments.vec_env.vector_envs.SerialVecEnv method)
(genrl.environments.vec_env.vector_envs.SubProcessVecEnv method)
(genrl.environments.vec_env.vector_envs.VecEnv method)
(genrl.environments.vec_env.wrappers.VecEnvWrapper method)
(genrl.utils.logger.CSVLogger method)
(genrl.utils.logger.HumanOutputFormat method)
(genrl.utils.logger.Logger method)
(genrl.utils.logger.TensorboardLogger method)
cnn() (in module genrl.utils.utils)
CNNActorCritic (class in genrl.core.actor_critic)
CnnCategoricalValue (class in genrl.core.values)
CnnDuelingValue (class in genrl.core.values)
CnnNoisyValue (class in genrl.core.values)
CNNPolicy (class in genrl.core.policies)
CnnValue (class in genrl.core.values)
collect_rewards() (genrl.agents.deep.base.onpolicy.OnPolicyAgent method)
collect_rollouts() (genrl.agents.deep.base.onpolicy.OnPolicyAgent method)
confidence (genrl.agents.bandits.multiarmed.bayesian.BayesianUCBMABAgent attribute)
(genrl.agents.bandits.multiarmed.ucb.UCBMABAgent attribute)
continue_training (genrl.core.rollout_storage.RolloutReturn attribute)
counts (genrl.agents.bandits.multiarmed.base.MABAgent attribute)
create_model (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.base.BaseAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
CSVLogger (class in genrl.utils.logger)
D
db (genrl.agents.bandits.contextual.common.transition.TransitionDB attribute)
db_size (genrl.agents.bandits.contextual.common.transition.TransitionDB attribute)
DCBAgent (class in genrl.agents.bandits.contextual.base)
DDPG (class in genrl.agents.deep.ddpg.ddpg)
ddqn_q_target() (in module genrl.agents.deep.dqn.utils)
device (genrl.agents.bandits.contextual.base.DCBAgent attribute)
(genrl.agents.bandits.contextual.common.transition.TransitionDB attribute)
(genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.base.BaseAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
discrete (genrl.core.actor_critic.MlpActorCritic attribute)
(genrl.core.actor_critic.MlpSharedActorCritic attribute)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic attribute)
(genrl.core.actor_critic.MlpSingleActorTwoCritic attribute)
dones (genrl.core.buffers.PrioritizedReplayBufferSamples attribute)
(genrl.core.buffers.ReplayBufferSamples attribute)
(genrl.core.rollout_storage.ReplayBufferSamples attribute)
DoubleDQN (class in genrl.agents.deep.dqn.double)
DQN (class in genrl.agents.deep.dqn.base)
DuelingDQN (class in genrl.agents.deep.dqn.dueling)
E
empty_logs() (genrl.agents.deep.a2c.a2c.A2C method)
(genrl.agents.deep.base.base.BaseAgent method)
(genrl.agents.deep.ddpg.ddpg.DDPG method)
(genrl.agents.deep.dqn.base.DQN method)
(genrl.agents.deep.ppo1.ppo1.PPO1 method)
(genrl.agents.deep.sac.sac.SAC method)
(genrl.agents.deep.td3.td3.TD3 method)
(genrl.agents.deep.vpg.vpg.VPG method)
entropy_coeff (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
entropy_tuning (genrl.agents.deep.sac.sac.SAC attribute)
env (genrl.agents.classical.qlearning.qlearning.QLearning attribute)
(genrl.agents.classical.sarsa.sarsa.SARSA attribute)
(genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.base.BaseAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
(in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
episode_reward (genrl.core.rollout_storage.RolloutReturn attribute)
episode_timesteps (genrl.core.rollout_storage.RolloutReturn attribute)
epochs (in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
eps (genrl.agents.bandits.multiarmed.epsgreedy.EpsGreedyMABAgent attribute)
EpsGreedyMABAgent (class in genrl.agents.bandits.multiarmed.epsgreedy)
epsilon (genrl.agents.classical.qlearning.qlearning.QLearning attribute)
(genrl.agents.classical.sarsa.sarsa.SARSA attribute)
epsilon_decay (genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
evaluate_actions() (genrl.agents.deep.a2c.a2c.A2C method)
(genrl.agents.deep.ppo1.ppo1.PPO1 method)
evaluate_episodes (in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
extend() (genrl.core.rollout_storage.BaseBuffer method)
F
fc_layers (genrl.core.values.CnnCategoricalValue attribute)
(genrl.core.values.CnnDuelingValue attribute)
(genrl.core.values.CnnNoisyValue attribute)
(genrl.core.values.MlpCategoricalValue attribute)
FireReset (class in genrl.environments.atari_wrappers)
FixedAgent (class in genrl.agents.bandits.contextual.fixed)
formats (genrl.utils.logger.Logger attribute)
forward() (genrl.agents.bandits.contextual.common.base_model.Model method)
(genrl.agents.bandits.contextual.common.bayesian.BayesianLinear method)
(genrl.agents.bandits.contextual.common.bayesian.BayesianNNBanditModel method)
(genrl.agents.bandits.contextual.common.neural.NeuralBanditModel method)
(genrl.core.actor_critic.MlpSingleActorTwoCritic method)
(genrl.core.base.BasePolicy method)
(genrl.core.base.BaseValue method)
(genrl.core.noise.NoisyLinear method)
(genrl.core.policies.CNNPolicy method)
(genrl.core.values.CnnCategoricalValue method)
(genrl.core.values.CnnDuelingValue method)
(genrl.core.values.CnnNoisyValue method)
(genrl.core.values.CnnValue method)
(genrl.core.values.MlpCategoricalValue method)
(genrl.core.values.MlpDuelingValue method)
FrameStack (class in genrl.environments.frame_stack)
framestack (genrl.core.values.CnnCategoricalValue attribute)
(genrl.core.values.CnnDuelingValue attribute)
G
gamma (genrl.agents.classical.qlearning.qlearning.QLearning attribute)
(genrl.agents.classical.sarsa.sarsa.SARSA attribute)
(genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.base.BaseAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
GaussianMAB (class in genrl.agents.bandits.multiarmed.gaussian_mab)
genrl.agents.bandits.contextual.base (module)
genrl.agents.bandits.contextual.bootstrap_neural (module)
genrl.agents.bandits.contextual.common.base_model (module)
genrl.agents.bandits.contextual.common.bayesian (module)
genrl.agents.bandits.contextual.common.neural (module)
genrl.agents.bandits.contextual.common.transition (module)
genrl.agents.bandits.contextual.fixed (module)
genrl.agents.bandits.contextual.linpos (module)
genrl.agents.bandits.contextual.neural_greedy (module)
genrl.agents.bandits.contextual.neural_linpos (module)
genrl.agents.bandits.contextual.neural_noise_sampling (module)
genrl.agents.bandits.contextual.variational (module)
genrl.agents.bandits.multiarmed.base (module)
genrl.agents.bandits.multiarmed.bayesian (module)
genrl.agents.bandits.multiarmed.bernoulli_mab (module)
genrl.agents.bandits.multiarmed.epsgreedy (module)
genrl.agents.bandits.multiarmed.gaussian_mab (module)
genrl.agents.bandits.multiarmed.gradient (module)
genrl.agents.bandits.multiarmed.thompson (module)
genrl.agents.bandits.multiarmed.ucb (module)
genrl.agents.classical.qlearning.qlearning (module)
genrl.agents.classical.sarsa.sarsa (module)
genrl.agents.deep.a2c.a2c (module)
genrl.agents.deep.base (module)
genrl.agents.deep.base.base (module)
genrl.agents.deep.base.offpolicy (module)
genrl.agents.deep.base.onpolicy (module)
genrl.agents.deep.ddpg.ddpg (module)
genrl.agents.deep.dqn.base (module)
genrl.agents.deep.dqn.categorical (module)
genrl.agents.deep.dqn.double (module)
genrl.agents.deep.dqn.dueling (module)
genrl.agents.deep.dqn.noisy (module)
genrl.agents.deep.dqn.prioritized (module)
genrl.agents.deep.dqn.utils (module)
genrl.agents.deep.ppo1.ppo1 (module)
genrl.agents.deep.sac.sac (module)
genrl.agents.deep.td3.td3 (module)
genrl.agents.deep.vpg.vpg (module)
genrl.core.actor_critic (module)
genrl.core.base (module)
genrl.core.buffers (module)
genrl.core.noise (module)
genrl.core.policies (module)
genrl.core.rollout_storage (module)
genrl.core.values (module)
genrl.environments (module)
genrl.environments.action_wrappers (module)
genrl.environments.atari_preprocessing (module)
genrl.environments.atari_wrappers (module)
genrl.environments.base_wrapper (module)
genrl.environments.frame_stack (module)
genrl.environments.gym_wrapper (module)
genrl.environments.suite (module)
genrl.environments.time_limit (module)
genrl.environments.vec_env (module)
genrl.environments.vec_env.monitor (module)
genrl.environments.vec_env.normalize (module)
genrl.environments.vec_env.utils (module)
genrl.environments.vec_env.vector_envs (module)
genrl.environments.vec_env.wrappers (module)
genrl.trainers.ClassicalTrainer (module)
genrl.trainers.DCBTrainer (module)
genrl.trainers.MABTrainer (module)
genrl.trainers.OffPolicyTrainer (module)
genrl.trainers.OnPolicyTrainer (module)
genrl.trainers.Trainer (module)
genrl.utils.logger (module)
genrl.utils.models (module)
genrl.utils.utils (module)
get() (genrl.core.rollout_storage.RolloutBuffer method)
get_action() (genrl.agents.classical.qlearning.qlearning.QLearning method)
(genrl.agents.classical.sarsa.sarsa.SARSA method)
(genrl.core.actor_critic.CNNActorCritic method)
(genrl.core.actor_critic.MlpSharedActorCritic method)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic method)
(genrl.core.actor_critic.MlpSingleActorTwoCritic method)
(genrl.core.base.BaseActorCritic method)
(genrl.core.base.BasePolicy method)
get_actor_critic_from_name() (in module genrl.core.actor_critic)
get_alpha_loss() (genrl.agents.deep.sac.sac.SAC method)
get_data() (genrl.agents.bandits.contextual.common.transition.TransitionDB method)
get_data_for_action() (genrl.agents.bandits.contextual.common.transition.TransitionDB method)
get_env_properties() (in module genrl.utils.utils)
get_features() (genrl.core.actor_critic.MlpSharedActorCritic method)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic method)
get_greedy_action() (genrl.agents.deep.dqn.base.DQN method)
(genrl.agents.deep.dqn.categorical.CategoricalDQN method)
get_hyperparams() (genrl.agents.classical.qlearning.qlearning.QLearning method)
(genrl.agents.deep.a2c.a2c.A2C method)
(genrl.agents.deep.base.base.BaseAgent method)
(genrl.agents.deep.ddpg.ddpg.DDPG method)
(genrl.agents.deep.dqn.base.DQN method)
(genrl.agents.deep.ppo1.ppo1.PPO1 method)
(genrl.agents.deep.sac.sac.SAC method)
(genrl.agents.deep.td3.td3.TD3 method)
(genrl.agents.deep.vpg.vpg.VPG method)
get_log_probs() (genrl.agents.deep.vpg.vpg.VPG method)
get_logger_by_name() (in module genrl.utils.logger)
get_logging_params() (genrl.agents.deep.a2c.a2c.A2C method)
(genrl.agents.deep.base.base.BaseAgent method)
(genrl.agents.deep.ddpg.ddpg.DDPG method)
(genrl.agents.deep.dqn.base.DQN method)
(genrl.agents.deep.ppo1.ppo1.PPO1 method)
(genrl.agents.deep.sac.sac.SAC method)
(genrl.agents.deep.td3.td3.TD3 method)
(genrl.agents.deep.vpg.vpg.VPG method)
get_model() (in module genrl.utils.utils)
get_model_from_name() (in module genrl.utils.models)
get_p_loss() (genrl.agents.deep.base.offpolicy.OffPolicyAgentAC method)
(genrl.agents.deep.sac.sac.SAC method)
get_params() (genrl.core.actor_critic.CNNActorCritic method)
(genrl.core.actor_critic.MlpActorCritic method)
(genrl.core.actor_critic.MlpSharedActorCritic method)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic method)
(genrl.core.actor_critic.MlpSingleActorTwoCritic method)
get_policy_from_name() (in module genrl.core.policies)
get_q_loss() (genrl.agents.deep.base.offpolicy.OffPolicyAgent method)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC method)
(genrl.agents.deep.dqn.categorical.CategoricalDQN method)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN method)
get_q_values() (genrl.agents.deep.base.offpolicy.OffPolicyAgentAC method)
(genrl.agents.deep.dqn.base.DQN method)
(genrl.agents.deep.dqn.categorical.CategoricalDQN method)
get_spaces() (genrl.environments.vec_env.vector_envs.SerialVecEnv method)
(genrl.environments.vec_env.vector_envs.SubProcessVecEnv method)
get_target_q_values() (genrl.agents.deep.base.offpolicy.OffPolicyAgentAC method)
(genrl.agents.deep.dqn.base.DQN method)
(genrl.agents.deep.dqn.categorical.CategoricalDQN method)
(genrl.agents.deep.dqn.double.DoubleDQN method)
(genrl.agents.deep.sac.sac.SAC method)
get_traj_loss() (genrl.agents.deep.a2c.a2c.A2C method)
(genrl.agents.deep.ppo1.ppo1.PPO1 method)
(genrl.agents.deep.vpg.vpg.VPG method)
get_value() (genrl.core.actor_critic.CNNActorCritic method)
(genrl.core.actor_critic.MlpSharedActorCritic method)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic method)
(genrl.core.actor_critic.MlpSingleActorTwoCritic method)
(genrl.core.base.BaseActorCritic method)
(genrl.core.base.BaseValue method)
get_value_from_name() (in module genrl.core.values)
GradientMABAgent (class in genrl.agents.bandits.multiarmed.gradient)
GymEnv() (in module genrl.environments.suite)
GymWrapper (class in genrl.environments.gym_wrapper)
H
hidden (genrl.core.values.MlpDuelingValue attribute)
HumanOutputFormat (class in genrl.utils.logger)
I
images() (genrl.environments.vec_env.vector_envs.SerialVecEnv method)
in_features (genrl.core.noise.NoisyLinear attribute)
indices (genrl.core.buffers.PrioritizedReplayBufferSamples attribute)
is_empty() (genrl.utils.models.TabularModel method)
L
layers (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.base.BaseAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
LazyFrames (class in genrl.environments.frame_stack)
LinearPosteriorAgent (class in genrl.agents.bandits.contextual.linpos)
load_hyperparams (in module genrl.trainers.Trainer)
load_model (in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
load_weights (in module genrl.trainers.Trainer)
load_weights() (genrl.agents.deep.dqn.base.DQN method)
log_interval (in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
log_key (in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
log_mode (in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
logdir (genrl.utils.logger.Logger attribute)
(in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
Logger (class in genrl.utils.logger)
lr (genrl.agents.classical.qlearning.qlearning.QLearning attribute)
(genrl.agents.classical.sarsa.sarsa.SARSA attribute)
lr_policy (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.base.BaseAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
lr_value (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.base.BaseAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
M
MABAgent (class in genrl.agents.bandits.multiarmed.base)
max_ep_len (in module genrl.trainers.OffPolicyTrainer)
max_epsilon (genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
max_key_len() (genrl.utils.logger.HumanOutputFormat method)
max_timesteps (in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
mean (genrl.core.noise.ActionNoise attribute)
min_epsilon (genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
mlp() (in module genrl.utils.utils)
MlpActorCritic (class in genrl.core.actor_critic)
MlpCategoricalValue (class in genrl.core.values)
MlpDuelingValue (class in genrl.core.values)
MlpNoisyValue (class in genrl.core.values)
MlpPolicy (class in genrl.core.policies)
MlpSharedActorCritic (class in genrl.core.actor_critic)
MlpSharedSingleActorTwoCritic (class in genrl.core.actor_critic)
MlpSingleActorTwoCritic (class in genrl.core.actor_critic)
MlpValue (class in genrl.core.values)
Model (class in genrl.agents.bandits.contextual.common.base_model)
N
n_envs (genrl.environments.vec_env.vector_envs.VecEnv attribute)
(in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
n_episodes (genrl.core.rollout_storage.RolloutReturn attribute)
network (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.base.BaseAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
NeuralBanditModel (class in genrl.agents.bandits.contextual.common.neural)
NeuralGreedyAgent (class in genrl.agents.bandits.contextual.neural_greedy)
NeuralLinearPosteriorAgent (class in genrl.agents.bandits.contextual.neural_linpos)
NeuralNoiseSamplingAgent (class in genrl.agents.bandits.contextual.neural_noise_sampling)
next_observations (genrl.core.rollout_storage.ReplayBufferSamples attribute)
next_states (genrl.core.buffers.PrioritizedReplayBufferSamples attribute)
(genrl.core.buffers.ReplayBufferSamples attribute)
noise (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
noise_std (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
noisy_layers (genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.core.values.CnnCategoricalValue attribute)
(genrl.core.values.CnnNoisyValue attribute)
(genrl.core.values.MlpCategoricalValue attribute)
noisy_mlp() (in module genrl.utils.utils)
NoisyDQN (class in genrl.agents.deep.dqn.noisy)
NoisyLinear (class in genrl.core.noise)
NoopReset (class in genrl.environments.atari_wrappers)
NormalActionNoise (class in genrl.core.noise)
num_atoms (genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.core.values.CnnCategoricalValue attribute)
(genrl.core.values.CnnNoisyValue attribute)
(genrl.core.values.MlpCategoricalValue attribute)
num_critics (genrl.core.actor_critic.MlpSharedSingleActorTwoCritic attribute)
(genrl.core.actor_critic.MlpSingleActorTwoCritic attribute)
O
obs_shape (genrl.environments.gym_wrapper.GymWrapper attribute)
(genrl.environments.vec_env.vector_envs.VecEnv attribute)
observation_spaces (genrl.environments.vec_env.vector_envs.VecEnv attribute)
observations (genrl.core.rollout_storage.ReplayBufferSamples attribute)
(genrl.core.rollout_storage.RolloutBufferSamples attribute)
off_policy (in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
OffPolicyAgent (class in genrl.agents.deep.base.offpolicy)
OffPolicyAgentAC (class in genrl.agents.deep.base.offpolicy)
old_log_prob (genrl.core.rollout_storage.RolloutBufferSamples attribute)
old_values (genrl.core.rollout_storage.RolloutBufferSamples attribute)
OnPolicyAgent (class in genrl.agents.deep.base.onpolicy)
OrnsteinUhlenbeckActionNoise (class in genrl.core.noise)
out_features (genrl.core.noise.NoisyLinear attribute)
P
policy_frequency (genrl.agents.deep.td3.td3.TD3 attribute)
policy_layers (genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
(genrl.core.actor_critic.MlpActorCritic attribute)
(genrl.core.actor_critic.MlpSharedActorCritic attribute)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic attribute)
(genrl.core.actor_critic.MlpSingleActorTwoCritic attribute)
polyak (genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
pos (genrl.core.buffers.PrioritizedBuffer attribute)
PPO1 (class in genrl.agents.deep.ppo1.ppo1)
prioritized_q_loss() (in module genrl.agents.deep.dqn.utils)
PrioritizedBuffer (class in genrl.core.buffers)
PrioritizedReplayBufferSamples (class in genrl.core.buffers)
PrioritizedReplayDQN (class in genrl.agents.deep.dqn.prioritized)
probability_hist (genrl.agents.bandits.multiarmed.gradient.GradientMABAgent attribute)
push() (genrl.core.buffers.PrioritizedBuffer method)
(genrl.core.buffers.ReplayBuffer method)
Q
QLearning (class in genrl.agents.classical.qlearning.qlearning)
quality (genrl.agents.bandits.multiarmed.bayesian.BayesianUCBMABAgent attribute)
(genrl.agents.bandits.multiarmed.epsgreedy.EpsGreedyMABAgent attribute)
(genrl.agents.bandits.multiarmed.gradient.GradientMABAgent attribute)
(genrl.agents.bandits.multiarmed.thompson.ThompsonSamplingMABAgent attribute)
(genrl.agents.bandits.multiarmed.ucb.UCBMABAgent attribute)
R
regret (genrl.agents.bandits.multiarmed.base.MABAgent attribute)
regret_hist (genrl.agents.bandits.multiarmed.base.MABAgent attribute)
render (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.base.BaseAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
(in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
render() (genrl.environments.base_wrapper.BaseWrapper method)
(genrl.environments.gym_wrapper.GymWrapper method)
(genrl.environments.vec_env.vector_envs.SerialVecEnv method)
(genrl.environments.vec_env.wrappers.VecEnvWrapper method)
replay_size (genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
ReplayBuffer (class in genrl.core.buffers)
ReplayBufferSamples (class in genrl.core.buffers)
(class in genrl.core.rollout_storage)
RescaleAction (class in genrl.environments.action_wrappers)
reset() (genrl.core.noise.NormalActionNoise method)
(genrl.core.noise.OrnsteinUhlenbeckActionNoise method)
(genrl.core.rollout_storage.BaseBuffer method)
(genrl.core.rollout_storage.RolloutBuffer method)
(genrl.environments.atari_preprocessing.AtariPreprocessing method)
(genrl.environments.atari_wrappers.FireReset method)
(genrl.environments.atari_wrappers.NoopReset method)
(genrl.environments.base_wrapper.BaseWrapper method)
(genrl.environments.frame_stack.FrameStack method)
(genrl.environments.gym_wrapper.GymWrapper method)
(genrl.environments.time_limit.AtariTimeLimit method)
(genrl.environments.time_limit.TimeLimit method)
(genrl.environments.vec_env.monitor.VecMonitor method)
(genrl.environments.vec_env.normalize.VecNormalize method)
(genrl.environments.vec_env.vector_envs.SerialVecEnv method)
(genrl.environments.vec_env.vector_envs.SubProcessVecEnv method)
(genrl.environments.vec_env.vector_envs.VecEnv method)
(genrl.environments.vec_env.wrappers.VecEnvWrapper method)
reset_noise() (genrl.core.noise.NoisyLinear method)
(genrl.core.values.MlpNoisyValue method)
reset_parameters() (genrl.agents.bandits.contextual.common.bayesian.BayesianLinear method)
(genrl.core.noise.NoisyLinear method)
reset_single_env() (genrl.environments.vec_env.vector_envs.SerialVecEnv method)
returns (genrl.core.rollout_storage.RolloutBufferSamples attribute)
reward_hist (genrl.agents.bandits.multiarmed.base.MABAgent attribute)
rewards (genrl.core.buffers.PrioritizedReplayBufferSamples attribute)
(genrl.core.buffers.ReplayBufferSamples attribute)
(genrl.core.rollout_storage.ReplayBufferSamples attribute)
rollout_size (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
RolloutBuffer (class in genrl.core.rollout_storage)
RolloutBufferSamples (class in genrl.core.rollout_storage)
RolloutReturn (class in genrl.core.rollout_storage)
round() (genrl.utils.logger.HumanOutputFormat method)
run_num (in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
RunningMeanStd (class in genrl.environments.vec_env.utils)
S
SAC (class in genrl.agents.deep.sac.sac)
sac (genrl.core.actor_critic.MlpActorCritic attribute)
(genrl.core.actor_critic.MlpSharedActorCritic attribute)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic attribute)
(genrl.core.actor_critic.MlpSingleActorTwoCritic attribute)
safe_mean() (in module genrl.utils.utils)
sample() (genrl.core.buffers.PrioritizedBuffer method)
(genrl.core.buffers.ReplayBuffer method)
(genrl.core.rollout_storage.BaseBuffer method)
(genrl.environments.gym_wrapper.GymWrapper method)
(genrl.environments.vec_env.vector_envs.VecEnv method)
(genrl.utils.models.TabularModel method)
sample_from_buffer() (genrl.agents.deep.base.offpolicy.OffPolicyAgent method)
SARSA (class in genrl.agents.classical.sarsa.sarsa)
save_interval (in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
save_model (in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
seed (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.base.base.BaseAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent attribute)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC attribute)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
(genrl.agents.deep.dqn.double.DoubleDQN attribute)
(genrl.agents.deep.dqn.dueling.DuelingDQN attribute)
(genrl.agents.deep.dqn.noisy.NoisyDQN attribute)
(genrl.agents.deep.dqn.prioritized.PrioritizedReplayDQN attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
(in module genrl.trainers.OffPolicyTrainer)
(in module genrl.trainers.OnPolicyTrainer)
(in module genrl.trainers.Trainer)
seed() (genrl.environments.base_wrapper.BaseWrapper method)
(genrl.environments.gym_wrapper.GymWrapper method)
(genrl.environments.vec_env.vector_envs.SubProcessVecEnv method)
(genrl.environments.vec_env.vector_envs.VecEnv method)
select_action() (genrl.agents.bandits.contextual.base.DCBAgent method)
(genrl.agents.bandits.contextual.bootstrap_neural.BootstrapNeuralAgent method)
(genrl.agents.bandits.contextual.fixed.FixedAgent method)
(genrl.agents.bandits.contextual.linpos.LinearPosteriorAgent method)
(genrl.agents.bandits.contextual.neural_greedy.NeuralGreedyAgent method)
(genrl.agents.bandits.contextual.neural_linpos.NeuralLinearPosteriorAgent method)
(genrl.agents.bandits.contextual.neural_noise_sampling.NeuralNoiseSamplingAgent method)
(genrl.agents.bandits.contextual.variational.VariationalAgent method)
(genrl.agents.bandits.multiarmed.base.MABAgent method)
(genrl.agents.bandits.multiarmed.bayesian.BayesianUCBMABAgent method)
(genrl.agents.bandits.multiarmed.epsgreedy.EpsGreedyMABAgent method)
(genrl.agents.bandits.multiarmed.gradient.GradientMABAgent method)
(genrl.agents.bandits.multiarmed.thompson.ThompsonSamplingMABAgent method)
(genrl.agents.bandits.multiarmed.ucb.UCBMABAgent method)
(genrl.agents.deep.a2c.a2c.A2C method)
(genrl.agents.deep.base.base.BaseAgent method)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC method)
(genrl.agents.deep.dqn.base.DQN method)
(genrl.agents.deep.ppo1.ppo1.PPO1 method)
(genrl.agents.deep.sac.sac.SAC method)
(genrl.agents.deep.vpg.vpg.VPG method)
SerialVecEnv (class in genrl.environments.vec_env.vector_envs)
set_seeds() (in module genrl.utils.utils)
shape (genrl.environments.frame_stack.LazyFrames attribute)
shared_layers (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.ddpg.ddpg.DDPG attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
(genrl.core.actor_critic.MlpSharedActorCritic attribute)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic attribute)
size() (genrl.core.rollout_storage.BaseBuffer method)
start_update (in module genrl.trainers.OffPolicyTrainer)
state_dim (genrl.core.actor_critic.MlpActorCritic attribute)
(genrl.core.actor_critic.MlpSharedActorCritic attribute)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic attribute)
(genrl.core.actor_critic.MlpSingleActorTwoCritic attribute)
(genrl.core.values.CnnNoisyValue attribute)
(genrl.core.values.MlpCategoricalValue attribute)
(genrl.core.values.MlpDuelingValue attribute)
states (genrl.core.buffers.PrioritizedReplayBufferSamples attribute)
(genrl.core.buffers.ReplayBufferSamples attribute)
std (genrl.core.noise.ActionNoise attribute)
std_init (genrl.core.noise.NoisyLinear attribute)
step() (genrl.environments.atari_preprocessing.AtariPreprocessing method)
(genrl.environments.atari_wrappers.NoopReset method)
(genrl.environments.base_wrapper.BaseWrapper method)
(genrl.environments.frame_stack.FrameStack method)
(genrl.environments.gym_wrapper.GymWrapper method)
(genrl.environments.time_limit.AtariTimeLimit method)
(genrl.environments.time_limit.TimeLimit method)
(genrl.environments.vec_env.monitor.VecMonitor method)
(genrl.environments.vec_env.normalize.VecNormalize method)
(genrl.environments.vec_env.vector_envs.SerialVecEnv method)
(genrl.environments.vec_env.vector_envs.SubProcessVecEnv method)
(genrl.environments.vec_env.vector_envs.VecEnv method)
(genrl.environments.vec_env.wrappers.VecEnvWrapper method)
(genrl.utils.models.TabularModel method)
SubProcessVecEnv (class in genrl.environments.vec_env.vector_envs)
swap_and_flatten() (genrl.core.rollout_storage.BaseBuffer static method)
T
TabularModel (class in genrl.utils.models)
TD3 (class in genrl.agents.deep.td3.td3)
temp (genrl.agents.bandits.multiarmed.gradient.GradientMABAgent attribute)
TensorboardLogger (class in genrl.utils.logger)
ThompsonSamplingMABAgent (class in genrl.agents.bandits.multiarmed.thompson)
TimeLimit (class in genrl.environments.time_limit)
to_torch() (genrl.core.rollout_storage.BaseBuffer method)
train_model() (genrl.agents.bandits.contextual.common.base_model.Model method)
TransitionDB (class in genrl.agents.bandits.contextual.common.transition)
U
UCBMABAgent (class in genrl.agents.bandits.multiarmed.ucb)
update() (genrl.agents.classical.qlearning.qlearning.QLearning method)
(genrl.agents.classical.sarsa.sarsa.SARSA method)
(genrl.environments.vec_env.utils.RunningMeanStd method)
update_db() (genrl.agents.bandits.contextual.bootstrap_neural.BootstrapNeuralAgent method)
(genrl.agents.bandits.contextual.fixed.FixedAgent method)
(genrl.agents.bandits.contextual.linpos.LinearPosteriorAgent method)
(genrl.agents.bandits.contextual.neural_greedy.NeuralGreedyAgent method)
(genrl.agents.bandits.contextual.neural_linpos.NeuralLinearPosteriorAgent method)
(genrl.agents.bandits.contextual.neural_noise_sampling.NeuralNoiseSamplingAgent method)
(genrl.agents.bandits.contextual.variational.VariationalAgent method)
update_interval (in module genrl.trainers.OffPolicyTrainer)
update_parameters() (genrl.agents.bandits.contextual.base.DCBAgent method)
update_params() (genrl.agents.bandits.contextual.bootstrap_neural.BootstrapNeuralAgent method)
(genrl.agents.bandits.contextual.fixed.FixedAgent method)
(genrl.agents.bandits.contextual.linpos.LinearPosteriorAgent method)
(genrl.agents.bandits.contextual.neural_greedy.NeuralGreedyAgent method)
(genrl.agents.bandits.contextual.neural_linpos.NeuralLinearPosteriorAgent method)
(genrl.agents.bandits.contextual.neural_noise_sampling.NeuralNoiseSamplingAgent method)
(genrl.agents.bandits.contextual.variational.VariationalAgent method)
(genrl.agents.bandits.multiarmed.base.MABAgent method)
(genrl.agents.bandits.multiarmed.bayesian.BayesianUCBMABAgent method)
(genrl.agents.bandits.multiarmed.epsgreedy.EpsGreedyMABAgent method)
(genrl.agents.bandits.multiarmed.gradient.GradientMABAgent method)
(genrl.agents.bandits.multiarmed.thompson.ThompsonSamplingMABAgent method)
(genrl.agents.bandits.multiarmed.ucb.UCBMABAgent method)
(genrl.agents.deep.a2c.a2c.A2C method)
(genrl.agents.deep.base.offpolicy.OffPolicyAgent method)
(genrl.agents.deep.base.onpolicy.OnPolicyAgent method)
(genrl.agents.deep.ddpg.ddpg.DDPG method)
(genrl.agents.deep.dqn.base.DQN method)
(genrl.agents.deep.ppo1.ppo1.PPO1 method)
(genrl.agents.deep.sac.sac.SAC method)
(genrl.agents.deep.td3.td3.TD3 method)
(genrl.agents.deep.vpg.vpg.VPG method)
update_params_before_select_action() (genrl.agents.deep.base.offpolicy.OffPolicyAgent method)
(genrl.agents.deep.dqn.base.DQN method)
update_priorities() (genrl.core.buffers.PrioritizedBuffer method)
update_target_model() (genrl.agents.deep.base.offpolicy.OffPolicyAgent method)
(genrl.agents.deep.base.offpolicy.OffPolicyAgentAC method)
(genrl.agents.deep.dqn.base.DQN method)
(genrl.agents.deep.sac.sac.SAC method)
use_dropout (genrl.agents.bandits.contextual.common.base_model.Model attribute)
(genrl.agents.bandits.contextual.common.bayesian.BayesianNNBanditModel attribute)
(genrl.agents.bandits.contextual.common.neural.NeuralBanditModel attribute)
V
v_max (genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
v_min (genrl.agents.deep.dqn.categorical.CategoricalDQN attribute)
val_type (genrl.core.actor_critic.MlpActorCritic attribute)
(genrl.core.actor_critic.MlpSharedActorCritic attribute)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic attribute)
(genrl.core.actor_critic.MlpSingleActorTwoCritic attribute)
value_coeff (genrl.agents.deep.a2c.a2c.A2C attribute)
(genrl.agents.deep.ppo1.ppo1.PPO1 attribute)
value_layers (genrl.agents.deep.dqn.base.DQN attribute)
(genrl.agents.deep.sac.sac.SAC attribute)
(genrl.agents.deep.td3.td3.TD3 attribute)
(genrl.core.actor_critic.MlpActorCritic attribute)
(genrl.core.actor_critic.MlpSharedActorCritic attribute)
(genrl.core.actor_critic.MlpSharedSingleActorTwoCritic attribute)
(genrl.core.actor_critic.MlpSingleActorTwoCritic attribute)
VariationalAgent (class in genrl.agents.bandits.contextual.variational)
VecEnv (class in genrl.environments.vec_env.vector_envs)
VecEnvWrapper (class in genrl.environments.vec_env.wrappers)
VecMonitor (class in genrl.environments.vec_env.monitor)
VecNormalize (class in genrl.environments.vec_env.normalize)
VectorEnv() (in module genrl.environments.suite)
VPG (class in genrl.agents.deep.vpg.vpg)
W
warmup_steps (in module genrl.trainers.OffPolicyTrainer)
weights (genrl.core.buffers.PrioritizedReplayBufferSamples attribute)
worker() (in module genrl.environments.vec_env.vector_envs)
write() (genrl.utils.logger.CSVLogger method)
(genrl.utils.logger.HumanOutputFormat method)
(genrl.utils.logger.Logger method)
(genrl.utils.logger.TensorboardLogger method)
write_to_file() (genrl.utils.logger.HumanOutputFormat method)
Read the Docs
v: latest
Versions
latest
stable
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds
Free document hosting provided by
Read the Docs
.