Index

A

A2C (class in nnabla_rl.algorithms.a2c) A2CConfig (class in nnabla_rl.algorithms.a2c) action() (nnabla_rl.environment_explorer.EnvironmentExplorer method) (nnabla_rl.environment_explorers.GaussianExplorer method) (nnabla_rl.environment_explorers.LinearDecayEpsilonGreedyExplorer method) (nnabla_rl.environment_explorers.RawPolicyExplorer method) action_dim (nnabla_rl.environments.environment_info.EnvironmentInfo property) action_high (nnabla_rl.environments.environment_info.EnvironmentInfo property) action_low (nnabla_rl.environments.environment_info.EnvironmentInfo property) action_shape (nnabla_rl.environments.environment_info.EnvironmentInfo property) Algorithm (class in nnabla_rl.algorithm) AlgorithmConfig (class in nnabla_rl.algorithm) all_probs() (nnabla_rl.models.ValueDistributionFunction method) all_q() (nnabla_rl.models.QFunction method) all_quantile_values() (nnabla_rl.models.StateActionQuantileFunction method) all_quantiles() (nnabla_rl.models.QuantileDistributionFunction method)

AMP (class in nnabla_rl.algorithms.amp) AMPConfig (class in nnabla_rl.algorithms.amp) append() (nnabla_rl.replay_buffer.ReplayBuffer method) (nnabla_rl.replay_buffers.HindsightReplayBuffer method) (nnabla_rl.replay_buffers.MemoryEfficientAtariBuffer method) (nnabla_rl.replay_buffers.PrioritizedReplayBuffer method) (nnabla_rl.replay_buffers.TrajectoryReplayBuffer method) append_all() (nnabla_rl.replay_buffer.ReplayBuffer method) (nnabla_rl.replay_buffers.PrioritizedReplayBuffer method) (nnabla_rl.replay_buffers.TrajectoryReplayBuffer method) argmax() (in module nnabla_rl.functions) argmax_q() (nnabla_rl.models.QFunction method) as_q_function() (nnabla_rl.models.QuantileDistributionFunction method) (nnabla_rl.models.StateActionQuantileFunction method) (nnabla_rl.models.ValueDistributionFunction method) ATRPO (class in nnabla_rl.algorithms.atrpo) ATRPOConfig (class in nnabla_rl.algorithms.atrpo)

B

batch_flatten() (in module nnabla_rl.functions) BCQ (class in nnabla_rl.algorithms.bcq) BCQConfig (class in nnabla_rl.algorithms.bcq) BEAR (class in nnabla_rl.algorithms.bear) BEARConfig (class in nnabla_rl.algorithms.bear)

Bernoulli (class in nnabla_rl.distributions) build_explorer() (nnabla_rl.builders.ExplorerBuilder method) build_model() (nnabla_rl.builders.ModelBuilder method) build_preprocessor() (nnabla_rl.builders.PreprocessorBuilder method) build_replay_buffer() (nnabla_rl.builders.ReplayBufferBuilder method) build_solver() (nnabla_rl.builders.SolverBuilder method)

C

capacity (nnabla_rl.replay_buffer.ReplayBuffer property) (nnabla_rl.replay_buffers.PrioritizedReplayBuffer property) CategoricalDDQN (class in nnabla_rl.algorithms.categorical_ddqn) CategoricalDDQNConfig (class in nnabla_rl.algorithms.categorical_ddqn) CategoricalDQN (class in nnabla_rl.algorithms.categorical_dqn) CategoricalDQNConfig (class in nnabla_rl.algorithms.categorical_dqn) choose_probable() (nnabla_rl.distributions.Bernoulli method) (nnabla_rl.distributions.Distribution method) (nnabla_rl.distributions.Gaussian method) (nnabla_rl.distributions.OneHotSoftmax method) (nnabla_rl.distributions.Softmax method) (nnabla_rl.distributions.SquashedGaussian method) clear_parameters() (nnabla_rl.models.model.Model method) compute_eval_action() (nnabla_rl.algorithm.Algorithm method) (nnabla_rl.algorithms.a2c.A2C method) (nnabla_rl.algorithms.amp.AMP method) (nnabla_rl.algorithms.atrpo.ATRPO method) (nnabla_rl.algorithms.bcq.BCQ method) (nnabla_rl.algorithms.bear.BEAR method) (nnabla_rl.algorithms.categorical_dqn.CategoricalDQN method) (nnabla_rl.algorithms.ddp.DDP method) (nnabla_rl.algorithms.ddpg.DDPG method) (nnabla_rl.algorithms.decision_transformer.DecisionTransformer method) (nnabla_rl.algorithms.demme_sac.DEMMESAC method) (nnabla_rl.algorithms.dqn.DQN method) (nnabla_rl.algorithms.gail.GAIL method) (nnabla_rl.algorithms.icml2015_trpo.ICML2015TRPO method) (nnabla_rl.algorithms.icml2018_sac.ICML2018SAC method) (nnabla_rl.algorithms.iqn.IQN method) (nnabla_rl.algorithms.lqr.LQR method) (nnabla_rl.algorithms.mppi.MPPI method) (nnabla_rl.algorithms.option_critic.OptionCritic method) (nnabla_rl.algorithms.ppo.PPO method) (nnabla_rl.algorithms.qrdqn.QRDQN method) (nnabla_rl.algorithms.reinforce.REINFORCE method) (nnabla_rl.algorithms.sac.SAC method) (nnabla_rl.algorithms.td3.TD3 method) (nnabla_rl.algorithms.trpo.TRPO method) (nnabla_rl.algorithms.xql.XQL method)

compute_trajectory() (nnabla_rl.algorithm.Algorithm method) (nnabla_rl.algorithms.ddp.DDP method) (nnabla_rl.algorithms.lqr.LQR method) (nnabla_rl.algorithms.mppi.MPPI method) concat_interleave() (in module nnabla_rl.functions)

D

DDP (class in nnabla_rl.algorithms.ddp) DDPConfig (class in nnabla_rl.algorithms.ddp) DDPG (class in nnabla_rl.algorithms.ddpg) DDPGConfig (class in nnabla_rl.algorithms.ddpg) DDQN (class in nnabla_rl.algorithms.ddqn) DDQNConfig (class in nnabla_rl.algorithms.ddqn) DecisionTransformer (class in nnabla_rl.algorithms.decision_transformer) DecisionTransformerConfig (class in nnabla_rl.algorithms.decision_transformer) decode() (nnabla_rl.models.VariationalAutoEncoder method) decode_multiple() (nnabla_rl.models.VariationalAutoEncoder method)

DecorableReplayBuffer (class in nnabla_rl.replay_buffers) deepcopy() (nnabla_rl.models.model.Model method) DEMMESAC (class in nnabla_rl.algorithms.demme_sac) DEMMESACConfig (class in nnabla_rl.algorithms.demme_sac) DeterministicPolicy (class in nnabla_rl.models) Distribution (class in nnabla_rl.distributions) DQN (class in nnabla_rl.algorithms.dqn) DQNConfig (class in nnabla_rl.algorithms.dqn) DRQN (class in nnabla_rl.algorithms.drqn) DRQNConfig (class in nnabla_rl.algorithms.drqn)

E

EfficientSRSAC (class in nnabla_rl.algorithms.srsac) EfficientSRSACConfig (class in nnabla_rl.algorithms.srsac) encode() (nnabla_rl.models.Encoder method) encode_and_decode() (nnabla_rl.models.VariationalAutoEncoder method) Encoder (class in nnabla_rl.models) entropy() (nnabla_rl.distributions.Bernoulli method) (nnabla_rl.distributions.Distribution method) (nnabla_rl.distributions.Gaussian method) (nnabla_rl.distributions.Softmax method)

EnvironmentExplorer (class in nnabla_rl.environment_explorer) EnvironmentExplorerConfig (class in nnabla_rl.environment_explorer) EnvironmentInfo (class in nnabla_rl.environments.environment_info) EvaluationHook (class in nnabla_rl.hooks) expand_dims() (in module nnabla_rl.functions) ExplorerBuilder (class in nnabla_rl.builders)

F

from_env() (nnabla_rl.environments.environment_info.EnvironmentInfo static method)

G

GAIL (class in nnabla_rl.algorithms.gail) GAILConfig (class in nnabla_rl.algorithms.gail) Gaussian (class in nnabla_rl.distributions)

gaussian_cross_entropy_method() (in module nnabla_rl.functions) GaussianExplorer (class in nnabla_rl.environment_explorers) get_internal_states() (nnabla_rl.models.model.Model method) get_parameters() (nnabla_rl.models.model.Model method)

H

HER (class in nnabla_rl.algorithms.her) HERConfig (class in nnabla_rl.algorithms.her) HindsightReplayBuffer (class in nnabla_rl.replay_buffers)

Hook (class in nnabla_rl.hook) HyAR (class in nnabla_rl.algorithms.hyar) HyARConfig (class in nnabla_rl.algorithms.hyar)

I

ICML2015TRPO (class in nnabla_rl.algorithms.icml2015_trpo) ICML2015TRPOConfig (class in nnabla_rl.algorithms.icml2015_trpo) ICML2018SAC (class in nnabla_rl.algorithms.icml2018_sac) ICML2018SACConfig (class in nnabla_rl.algorithms.icml2018_sac) ICRA2018QtOpt (class in nnabla_rl.algorithms.icra2018_qtopt), [1] iLQR (class in nnabla_rl.algorithms.ilqr) iLQRConfig (class in nnabla_rl.algorithms.ilqr) internal_state_shapes() (nnabla_rl.models.model.Model method) IQN (class in nnabla_rl.algorithms.iqn) IQNConfig (class in nnabla_rl.algorithms.iqn) is_continuous_action_env() (nnabla_rl.environments.environment_info.EnvironmentInfo method) is_continuous_state_env() (nnabla_rl.environments.environment_info.EnvironmentInfo method) is_discrete_action_env() (nnabla_rl.environments.environment_info.EnvironmentInfo method) is_discrete_state_env() (nnabla_rl.environments.environment_info.EnvironmentInfo method) is_goal_conditioned_env() (nnabla_rl.environments.environment_info.EnvironmentInfo method) is_mixed_action_env() (nnabla_rl.environments.environment_info.EnvironmentInfo method) is_mixed_state_env() (nnabla_rl.environments.environment_info.EnvironmentInfo method) is_recurrent() (nnabla_rl.models.model.Model method) is_rnn_supported() (nnabla_rl.algorithm.Algorithm class method) (nnabla_rl.algorithms.categorical_dqn.CategoricalDQN class method) (nnabla_rl.algorithms.ddpg.DDPG class method) (nnabla_rl.algorithms.decision_transformer.DecisionTransformer class method) (nnabla_rl.algorithms.demme_sac.DEMMESAC class method) (nnabla_rl.algorithms.dqn.DQN class method) (nnabla_rl.algorithms.hyar.HyAR class method) (nnabla_rl.algorithms.icml2018_sac.ICML2018SAC class method) (nnabla_rl.algorithms.iqn.IQN class method) (nnabla_rl.algorithms.mppi.MPPI class method) (nnabla_rl.algorithms.option_critic.OptionCritic class method) (nnabla_rl.algorithms.qrdqn.QRDQN class method) (nnabla_rl.algorithms.sac.SAC class method) (nnabla_rl.algorithms.srsac.EfficientSRSAC class method) (nnabla_rl.algorithms.td3.TD3 class method) (nnabla_rl.algorithms.xql.XQL class method)

is_supported_env() (nnabla_rl.algorithm.Algorithm class method) (nnabla_rl.algorithms.a2c.A2C class method) (nnabla_rl.algorithms.amp.AMP class method) (nnabla_rl.algorithms.atrpo.ATRPO class method) (nnabla_rl.algorithms.bcq.BCQ class method) (nnabla_rl.algorithms.bear.BEAR class method) (nnabla_rl.algorithms.categorical_dqn.CategoricalDQN class method) (nnabla_rl.algorithms.ddp.DDP class method) (nnabla_rl.algorithms.ddpg.DDPG class method) (nnabla_rl.algorithms.decision_transformer.DecisionTransformer class method) (nnabla_rl.algorithms.demme_sac.DEMMESAC class method) (nnabla_rl.algorithms.dqn.DQN class method) (nnabla_rl.algorithms.gail.GAIL class method) (nnabla_rl.algorithms.her.HER class method) (nnabla_rl.algorithms.hyar.HyAR class method) (nnabla_rl.algorithms.icml2015_trpo.ICML2015TRPO class method) (nnabla_rl.algorithms.icml2018_sac.ICML2018SAC class method) (nnabla_rl.algorithms.icra2018_qtopt.ICRA2018QtOpt class method), [1] (nnabla_rl.algorithms.iqn.IQN class method) (nnabla_rl.algorithms.lqr.LQR class method) (nnabla_rl.algorithms.mppi.MPPI class method) (nnabla_rl.algorithms.option_critic.OptionCritic class method) (nnabla_rl.algorithms.ppo.PPO class method) (nnabla_rl.algorithms.qrdqn.QRDQN class method) (nnabla_rl.algorithms.reinforce.REINFORCE class method) (nnabla_rl.algorithms.sac.SAC class method) (nnabla_rl.algorithms.td3.TD3 class method) (nnabla_rl.algorithms.trpo.TRPO class method) (nnabla_rl.algorithms.xql.XQL class method) is_tuple_action_env() (nnabla_rl.environments.environment_info.EnvironmentInfo method) is_tuple_state_env() (nnabla_rl.environments.environment_info.EnvironmentInfo method) iteration_num (nnabla_rl.algorithm.Algorithm property) IterationNumHook (class in nnabla_rl.hooks) IterationStateHook (class in nnabla_rl.hooks)

K

kl_divergence() (nnabla_rl.distributions.Bernoulli method) (nnabla_rl.distributions.Distribution method) (nnabla_rl.distributions.Gaussian method) (nnabla_rl.distributions.Softmax method)

L

latent_distribution() (nnabla_rl.models.VariationalAutoEncoder method) latest_iteration_state (nnabla_rl.algorithm.Algorithm property) (nnabla_rl.algorithms.a2c.A2C property) (nnabla_rl.algorithms.amp.AMP property) (nnabla_rl.algorithms.atrpo.ATRPO property) (nnabla_rl.algorithms.bcq.BCQ property) (nnabla_rl.algorithms.bear.BEAR property) (nnabla_rl.algorithms.categorical_dqn.CategoricalDQN property) (nnabla_rl.algorithms.ddpg.DDPG property) (nnabla_rl.algorithms.decision_transformer.DecisionTransformer property) (nnabla_rl.algorithms.demme_sac.DEMMESAC property) (nnabla_rl.algorithms.dqn.DQN property) (nnabla_rl.algorithms.gail.GAIL property) (nnabla_rl.algorithms.hyar.HyAR property) (nnabla_rl.algorithms.icml2015_trpo.ICML2015TRPO property) (nnabla_rl.algorithms.icml2018_sac.ICML2018SAC property) (nnabla_rl.algorithms.iqn.IQN property) (nnabla_rl.algorithms.mppi.MPPI property) (nnabla_rl.algorithms.option_critic.OptionCritic property) (nnabla_rl.algorithms.ppo.PPO property) (nnabla_rl.algorithms.qrdqn.QRDQN property) (nnabla_rl.algorithms.reinforce.REINFORCE property) (nnabla_rl.algorithms.sac.SAC property) (nnabla_rl.algorithms.srsac.EfficientSRSAC property) (nnabla_rl.algorithms.td3.TD3 property) (nnabla_rl.algorithms.trpo.TRPO property) (nnabla_rl.algorithms.xql.XQL property)

LinearDecayEpsilonGreedyExplorer (class in nnabla_rl.environment_explorers) load_parameters() (nnabla_rl.models.model.Model method) log_prob() (nnabla_rl.distributions.Bernoulli method) (nnabla_rl.distributions.Distribution method) (nnabla_rl.distributions.Gaussian method) (nnabla_rl.distributions.OneHotSoftmax method) (nnabla_rl.distributions.Softmax method) (nnabla_rl.distributions.SquashedGaussian method) LQR (class in nnabla_rl.algorithms.lqr) LQRConfig (class in nnabla_rl.algorithms.lqr)

M

max_q() (nnabla_rl.models.QFunction method) max_q_probs() (nnabla_rl.models.ValueDistributionFunction method) max_q_quantile_values() (nnabla_rl.models.StateActionQuantileFunction method) max_q_quantiles() (nnabla_rl.models.QuantileDistributionFunction method) mean() (nnabla_rl.distributions.Bernoulli method) (nnabla_rl.distributions.Distribution method) (nnabla_rl.distributions.Gaussian method) (nnabla_rl.distributions.Softmax method) mean_squared_error() (in module nnabla_rl.functions) MemoryEfficientAtariBuffer (class in nnabla_rl.replay_buffers) MemoryEfficientAtariTrajectoryBuffer (class in nnabla_rl.replay_buffers) minimum_n() (in module nnabla_rl.functions)

MMESAC (class in nnabla_rl.algorithms.mme_sac) MMESACConfig (class in nnabla_rl.algorithms.mme_sac) Model (class in nnabla_rl.models.model) ModelBuilder (class in nnabla_rl.builders) module nnabla_rl.functions nnabla_rl.parametric_functions MPPI (class in nnabla_rl.algorithms.mppi) MPPIConfig (class in nnabla_rl.algorithms.mppi) MunchausenDQN (class in nnabla_rl.algorithms.munchausen_dqn) MunchausenDQNConfig (class in nnabla_rl.algorithms.munchausen_dqn) MunchausenIQN (class in nnabla_rl.algorithms.munchausen_iqn) MunchausenIQNConfig (class in nnabla_rl.algorithms.munchausen_iqn)

N

ndim (nnabla_rl.distributions.Bernoulli property) (nnabla_rl.distributions.Distribution property) (nnabla_rl.distributions.Gaussian property) (nnabla_rl.distributions.OneHotSoftmax property) (nnabla_rl.distributions.Softmax property) (nnabla_rl.distributions.SquashedGaussian property)

nnabla_rl.functions module nnabla_rl.parametric_functions module noisy_net() (in module nnabla_rl.parametric_functions)

O

on_hook_called() (nnabla_rl.hook.Hook method) (nnabla_rl.hooks.EvaluationHook method) (nnabla_rl.hooks.IterationNumHook method) (nnabla_rl.hooks.IterationStateHook method) (nnabla_rl.hooks.ProgressBarHook method) (nnabla_rl.hooks.SaveSnapshotHook method) (nnabla_rl.hooks.TimeMeasuringHook method)

OneHotSoftmax (class in nnabla_rl.distributions) OptionCritic (class in nnabla_rl.algorithms.option_critic) OptionCriticConfig (class in nnabla_rl.algorithms.option_critic)

P

Perturbator (class in nnabla_rl.models) pi() (nnabla_rl.models.DeterministicPolicy method) (nnabla_rl.models.StochasticPolicy method) Policy (class in nnabla_rl.models) PPO (class in nnabla_rl.algorithms.ppo)

PPOConfig (class in nnabla_rl.algorithms.ppo) PreprocessorBuilder (class in nnabla_rl.builders) PrioritizedReplayBuffer (class in nnabla_rl.replay_buffers) probs() (nnabla_rl.models.ValueDistributionFunction method) ProgressBarHook (class in nnabla_rl.hooks) pytorch_equivalent_gather() (in module nnabla_rl.functions)

Q

q() (nnabla_rl.models.QFunction method) QFunction (class in nnabla_rl.models) QRDQN (class in nnabla_rl.algorithms.qrdqn) QRDQNConfig (class in nnabla_rl.algorithms.qrdqn) QRSAC (class in nnabla_rl.algorithms.qrsac)

QRSACConfig (class in nnabla_rl.algorithms.qrsac) quantile_huber_loss() (in module nnabla_rl.functions) quantile_values() (nnabla_rl.models.StateActionQuantileFunction method) QuantileDistributionFunction (class in nnabla_rl.models) quantiles() (nnabla_rl.models.QuantileDistributionFunction method)

R

r() (nnabla_rl.models.reward_function.RewardFunction method) Rainbow (class in nnabla_rl.algorithms.rainbow) RainbowConfig (class in nnabla_rl.algorithms.rainbow) random_shooting_method() (in module nnabla_rl.functions) RawPolicyExplorer (class in nnabla_rl.environment_explorers) REINFORCE (class in nnabla_rl.algorithms.reinforce)

REINFORCEConfig (class in nnabla_rl.algorithms.reinforce) repeat() (in module nnabla_rl.functions) ReplayBuffer (class in nnabla_rl.replay_buffer) ReplayBufferBuilder (class in nnabla_rl.builders) reset_internal_states() (nnabla_rl.models.model.Model method) RewardFunction (class in nnabla_rl.models.reward_function) rollout() (nnabla_rl.environment_explorer.EnvironmentExplorer method)

S

SAC (class in nnabla_rl.algorithms.sac) SACConfig (class in nnabla_rl.algorithms.sac) SACD (class in nnabla_rl.algorithms.sacd) SACDConfig (class in nnabla_rl.algorithms.sacd) sample() (nnabla_rl.distributions.Bernoulli method) (nnabla_rl.distributions.Distribution method) (nnabla_rl.distributions.Gaussian method) (nnabla_rl.distributions.OneHotSoftmax method) (nnabla_rl.distributions.Softmax method) (nnabla_rl.distributions.SquashedGaussian method) (nnabla_rl.replay_buffer.ReplayBuffer method) (nnabla_rl.replay_buffers.MemoryEfficientAtariTrajectoryBuffer method) (nnabla_rl.replay_buffers.PrioritizedReplayBuffer method) sample_and_compute_log_prob() (nnabla_rl.distributions.Bernoulli method) (nnabla_rl.distributions.Distribution method) (nnabla_rl.distributions.Gaussian method) (nnabla_rl.distributions.OneHotSoftmax method) (nnabla_rl.distributions.Softmax method) (nnabla_rl.distributions.SquashedGaussian method) sample_gaussian() (in module nnabla_rl.functions) sample_gaussian_multiple() (in module nnabla_rl.functions) sample_indices() (nnabla_rl.replay_buffer.ReplayBuffer method) (nnabla_rl.replay_buffers.HindsightReplayBuffer method) (nnabla_rl.replay_buffers.MemoryEfficientAtariTrajectoryBuffer method) (nnabla_rl.replay_buffers.PrioritizedReplayBuffer method) (nnabla_rl.replay_buffers.TrajectoryReplayBuffer method) sample_indices_portion() (nnabla_rl.replay_buffers.TrajectoryReplayBuffer method) sample_multiple() (nnabla_rl.distributions.Distribution method) (nnabla_rl.distributions.Gaussian method) (nnabla_rl.distributions.Softmax method) (nnabla_rl.distributions.SquashedGaussian method)

sample_multiple_and_compute_log_prob() (nnabla_rl.distributions.SquashedGaussian method) sample_tau() (nnabla_rl.models.StateActionQuantileFunction method) sample_trajectories() (nnabla_rl.replay_buffers.TrajectoryReplayBuffer method) sample_trajectories_portion() (nnabla_rl.replay_buffers.TrajectoryReplayBuffer method) save_parameters() (nnabla_rl.models.model.Model method) SaveSnapshotHook (class in nnabla_rl.hooks) scope_name (nnabla_rl.models.model.Model property) set_hooks() (nnabla_rl.algorithm.Algorithm method) set_internal_states() (nnabla_rl.models.model.Model method) setup() (nnabla_rl.hook.Hook method) (nnabla_rl.hooks.ProgressBarHook method) shallowcopy() (nnabla_rl.models.model.Model method) Softmax (class in nnabla_rl.distributions) SolverBuilder (class in nnabla_rl.builders) spatial_softmax() (in module nnabla_rl.parametric_functions) sqrt() (in module nnabla_rl.functions) SquashedGaussian (class in nnabla_rl.distributions) SRSAC (class in nnabla_rl.algorithms.srsac) SRSACConfig (class in nnabla_rl.algorithms.srsac) state_dim (nnabla_rl.environments.environment_info.EnvironmentInfo property) state_high (nnabla_rl.environments.environment_info.EnvironmentInfo property) state_low (nnabla_rl.environments.environment_info.EnvironmentInfo property) state_shape (nnabla_rl.environments.environment_info.EnvironmentInfo property) StateActionQuantileFunction (class in nnabla_rl.models) std() (in module nnabla_rl.functions) step() (nnabla_rl.environment_explorer.EnvironmentExplorer method) StochasticPolicy (class in nnabla_rl.models) swapaxes() (in module nnabla_rl.functions)

T

TD3 (class in nnabla_rl.algorithms.td3) TD3Config (class in nnabla_rl.algorithms.td3) teardown() (nnabla_rl.hook.Hook method) (nnabla_rl.hooks.ProgressBarHook method) TimeMeasuringHook (class in nnabla_rl.hooks) train() (nnabla_rl.algorithm.Algorithm method)

train_offline() (nnabla_rl.algorithm.Algorithm method) train_online() (nnabla_rl.algorithm.Algorithm method) TrajectoryReplayBuffer (class in nnabla_rl.replay_buffers) triangular_matrix() (in module nnabla_rl.functions) TRPO (class in nnabla_rl.algorithms.trpo) TRPOConfig (class in nnabla_rl.algorithms.trpo)

V

v() (nnabla_rl.models.VFunction method) ValueDistributionFunction (class in nnabla_rl.models)

VariationalAutoEncoder (class in nnabla_rl.models) VFunction (class in nnabla_rl.models)

X

XQL (class in nnabla_rl.algorithms.xql)

XQLConfig (class in nnabla_rl.algorithms.xql)