nnablaRL
v0.10.0
Installation
Example codes
Colab demos
nnablaRL APIs
nnablaRL
»
Index
Edit on GitHub
Index
A
|
B
|
C
|
D
|
E
|
F
|
G
|
H
|
I
|
K
|
L
|
M
|
N
|
O
|
P
|
Q
|
R
|
S
|
T
|
V
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)
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)
append_all() (nnabla_rl.replay_buffer.ReplayBuffer method)
(nnabla_rl.replay_buffers.PrioritizedReplayBuffer 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)
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)
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.Distribution method)
(nnabla_rl.distributions.Gaussian method)
(nnabla_rl.distributions.Softmax method)
(nnabla_rl.distributions.SquashedGaussian method)
compute_eval_action() (nnabla_rl.algorithm.Algorithm method)
(nnabla_rl.algorithms.a2c.A2C method)
(nnabla_rl.algorithms.bcq.BCQ method)
(nnabla_rl.algorithms.bear.BEAR method)
(nnabla_rl.algorithms.categorical_dqn.CategoricalDQN method)
(nnabla_rl.algorithms.ddpg.DDPG 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.munchausen_dqn.MunchausenDQN method)
(nnabla_rl.algorithms.munchausen_iqn.MunchausenIQN 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)
D
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)
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)
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)
E
encode() (nnabla_rl.models.Encoder method)
encode_and_decode() (nnabla_rl.models.VariationalAutoEncoder method)
Encoder (class in nnabla_rl.models)
entropy() (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_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)
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)
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_supported_env() (nnabla_rl.algorithm.Algorithm class 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.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.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.dqn.DQN property)
(nnabla_rl.algorithms.gail.GAIL property)
(nnabla_rl.algorithms.icml2015_trpo.ICML2015TRPO property)
(nnabla_rl.algorithms.icml2018_sac.ICML2018SAC property)
(nnabla_rl.algorithms.iqn.IQN property)
(nnabla_rl.algorithms.munchausen_dqn.MunchausenDQN property)
(nnabla_rl.algorithms.munchausen_iqn.MunchausenIQN 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.td3.TD3 property)
(nnabla_rl.algorithms.trpo.TRPO property)
LinearDecayEpsilonGreedyExplorer (class in nnabla_rl.environment_explorers)
load_parameters() (nnabla_rl.models.model.Model method)
log_prob() (nnabla_rl.distributions.Distribution method)
(nnabla_rl.distributions.Gaussian method)
(nnabla_rl.distributions.Softmax method)
(nnabla_rl.distributions.SquashedGaussian method)
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.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)
minimum_n() (in module nnabla_rl.functions)
Model (class in nnabla_rl.models.model)
ModelBuilder (class in nnabla_rl.builders)
module
nnabla_rl.functions
nnabla_rl.parametric_functions
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.Distribution property)
(nnabla_rl.distributions.Gaussian 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.SaveSnapshotHook method)
(nnabla_rl.hooks.TimeMeasuringHook method)
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)
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)
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)
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)
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)
sample() (nnabla_rl.distributions.Distribution method)
(nnabla_rl.distributions.Gaussian method)
(nnabla_rl.distributions.Softmax method)
(nnabla_rl.distributions.SquashedGaussian method)
(nnabla_rl.replay_buffer.ReplayBuffer method)
(nnabla_rl.replay_buffers.PrioritizedReplayBuffer method)
sample_and_compute_log_prob() (nnabla_rl.distributions.Distribution method)
(nnabla_rl.distributions.Gaussian 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.PrioritizedReplayBuffer 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)
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)
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)
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)
T
TD3 (class in nnabla_rl.algorithms.td3)
TD3Config (class in nnabla_rl.algorithms.td3)
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)
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)
Read the Docs
v: v0.10.0
Versions
latest
stable
v0.10.0
v0.9.0
Downloads
On Read the Docs
Project Home
Builds