d3rlpy
v0.91
Tutorials
Getting Started
Jupyter Notebooks
References
API Reference
Command Line Interface
Installation
Tips
Other
Paper Reproductions
License
d3rlpy
»
Index
Edit on GitHub
Index
_
|
A
|
B
|
C
|
D
|
E
|
F
|
G
|
I
|
L
|
M
|
N
|
O
|
P
|
Q
|
R
|
S
|
T
|
U
|
V
_
__getitem__() (d3rlpy.dataset.Episode method)
(d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.TransitionMiniBatch method)
__iter__() (d3rlpy.dataset.Episode method)
(d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.TransitionMiniBatch method)
__len__() (d3rlpy.dataset.Episode method)
(d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.TransitionMiniBatch method)
(d3rlpy.online.buffers.BatchReplayBuffer method)
(d3rlpy.online.buffers.ReplayBuffer method)
A
action (d3rlpy.dataset.Transition attribute)
action_scaler (d3rlpy.algos.AWAC attribute)
(d3rlpy.algos.AWR attribute)
(d3rlpy.algos.BC attribute)
(d3rlpy.algos.BCQ attribute)
(d3rlpy.algos.BEAR attribute)
(d3rlpy.algos.COMBO attribute)
(d3rlpy.algos.CQL attribute)
(d3rlpy.algos.CRR attribute)
(d3rlpy.algos.DDPG attribute)
(d3rlpy.algos.DiscreteAWR attribute)
(d3rlpy.algos.DiscreteBC attribute)
(d3rlpy.algos.DiscreteBCQ attribute)
(d3rlpy.algos.DiscreteCQL attribute)
(d3rlpy.algos.DiscreteRandomPolicy attribute)
(d3rlpy.algos.DiscreteSAC attribute)
(d3rlpy.algos.DoubleDQN attribute)
(d3rlpy.algos.DQN attribute)
(d3rlpy.algos.MOPO attribute)
(d3rlpy.algos.PLAS attribute)
(d3rlpy.algos.PLASWithPerturbation attribute)
(d3rlpy.algos.RandomPolicy attribute)
(d3rlpy.algos.SAC attribute)
(d3rlpy.algos.TD3 attribute)
(d3rlpy.algos.TD3PlusBC attribute)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics attribute)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
action_size (d3rlpy.algos.AWAC attribute)
(d3rlpy.algos.AWR attribute)
(d3rlpy.algos.BC attribute)
(d3rlpy.algos.BCQ attribute)
(d3rlpy.algos.BEAR attribute)
(d3rlpy.algos.COMBO attribute)
(d3rlpy.algos.CQL attribute)
(d3rlpy.algos.CRR attribute)
(d3rlpy.algos.DDPG attribute)
(d3rlpy.algos.DiscreteAWR attribute)
(d3rlpy.algos.DiscreteBC attribute)
(d3rlpy.algos.DiscreteBCQ attribute)
(d3rlpy.algos.DiscreteCQL attribute)
(d3rlpy.algos.DiscreteRandomPolicy attribute)
(d3rlpy.algos.DiscreteSAC attribute)
(d3rlpy.algos.DoubleDQN attribute)
(d3rlpy.algos.DQN attribute)
(d3rlpy.algos.MOPO attribute)
(d3rlpy.algos.PLAS attribute)
(d3rlpy.algos.PLASWithPerturbation attribute)
(d3rlpy.algos.RandomPolicy attribute)
(d3rlpy.algos.SAC attribute)
(d3rlpy.algos.TD3 attribute)
(d3rlpy.algos.TD3PlusBC attribute)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics attribute)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
actions (d3rlpy.dataset.Episode attribute)
(d3rlpy.dataset.MDPDataset attribute)
(d3rlpy.dataset.TransitionMiniBatch attribute)
active_logger (d3rlpy.algos.AWAC attribute)
(d3rlpy.algos.AWR attribute)
(d3rlpy.algos.BC attribute)
(d3rlpy.algos.BCQ attribute)
(d3rlpy.algos.BEAR attribute)
(d3rlpy.algos.COMBO attribute)
(d3rlpy.algos.CQL attribute)
(d3rlpy.algos.CRR attribute)
(d3rlpy.algos.DDPG attribute)
(d3rlpy.algos.DiscreteAWR attribute)
(d3rlpy.algos.DiscreteBC attribute)
(d3rlpy.algos.DiscreteBCQ attribute)
(d3rlpy.algos.DiscreteCQL attribute)
(d3rlpy.algos.DiscreteRandomPolicy attribute)
(d3rlpy.algos.DiscreteSAC attribute)
(d3rlpy.algos.DoubleDQN attribute)
(d3rlpy.algos.DQN attribute)
(d3rlpy.algos.MOPO attribute)
(d3rlpy.algos.PLAS attribute)
(d3rlpy.algos.PLASWithPerturbation attribute)
(d3rlpy.algos.RandomPolicy attribute)
(d3rlpy.algos.SAC attribute)
(d3rlpy.algos.TD3 attribute)
(d3rlpy.algos.TD3PlusBC attribute)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics attribute)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
AdamFactory (class in d3rlpy.models.optimizers)
add_additional_data() (d3rlpy.dataset.TransitionMiniBatch method)
append() (d3rlpy.dataset.MDPDataset method)
(d3rlpy.online.buffers.BatchReplayBuffer method)
(d3rlpy.online.buffers.ReplayBuffer method)
append_episode() (d3rlpy.online.buffers.BatchReplayBuffer method)
(d3rlpy.online.buffers.ReplayBuffer method)
average_value_estimation_scorer() (in module d3rlpy.metrics.scorer)
AWAC (class in d3rlpy.algos)
AWR (class in d3rlpy.algos)
B
batch_size (d3rlpy.algos.AWAC attribute)
(d3rlpy.algos.AWR attribute)
(d3rlpy.algos.BC attribute)
(d3rlpy.algos.BCQ attribute)
(d3rlpy.algos.BEAR attribute)
(d3rlpy.algos.COMBO attribute)
(d3rlpy.algos.CQL attribute)
(d3rlpy.algos.CRR attribute)
(d3rlpy.algos.DDPG attribute)
(d3rlpy.algos.DiscreteAWR attribute)
(d3rlpy.algos.DiscreteBC attribute)
(d3rlpy.algos.DiscreteBCQ attribute)
(d3rlpy.algos.DiscreteCQL attribute)
(d3rlpy.algos.DiscreteRandomPolicy attribute)
(d3rlpy.algos.DiscreteSAC attribute)
(d3rlpy.algos.DoubleDQN attribute)
(d3rlpy.algos.DQN attribute)
(d3rlpy.algos.MOPO attribute)
(d3rlpy.algos.PLAS attribute)
(d3rlpy.algos.PLASWithPerturbation attribute)
(d3rlpy.algos.RandomPolicy attribute)
(d3rlpy.algos.SAC attribute)
(d3rlpy.algos.TD3 attribute)
(d3rlpy.algos.TD3PlusBC attribute)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics attribute)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
BatchReplayBuffer (class in d3rlpy.online.buffers)
BC (class in d3rlpy.algos)
BCQ (class in d3rlpy.algos)
BEAR (class in d3rlpy.algos)
bootstrap (d3rlpy.models.q_functions.FQFQFunctionFactory attribute)
(d3rlpy.models.q_functions.IQNQFunctionFactory attribute)
(d3rlpy.models.q_functions.MeanQFunctionFactory attribute)
(d3rlpy.models.q_functions.QRQFunctionFactory attribute)
build_episodes() (d3rlpy.dataset.MDPDataset method)
build_transitions() (d3rlpy.dataset.Episode method)
build_with_dataset() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
build_with_env() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
C
clear_links() (d3rlpy.dataset.Transition method)
ClipRewardScaler (class in d3rlpy.preprocessing)
collect() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
COMBO (class in d3rlpy.algos)
compare_continuous_action_diff() (in module d3rlpy.metrics.comparer)
compare_discrete_action_match() (in module d3rlpy.metrics.comparer)
compute_epsilon() (d3rlpy.online.explorers.LinearDecayEpsilonGreedy method)
compute_return() (d3rlpy.dataset.Episode method)
compute_stats() (d3rlpy.dataset.MDPDataset method)
ConstantEpsilonGreedy (class in d3rlpy.online.explorers)
continuous_action_diff_scorer() (in module d3rlpy.metrics.scorer)
copy_policy_from() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
copy_q_function_from() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
CQL (class in d3rlpy.algos)
create() (d3rlpy.models.encoders.DefaultEncoderFactory method)
(d3rlpy.models.encoders.DenseEncoderFactory method)
(d3rlpy.models.encoders.PixelEncoderFactory method)
(d3rlpy.models.encoders.VectorEncoderFactory method)
(d3rlpy.models.optimizers.AdamFactory method)
(d3rlpy.models.optimizers.OptimizerFactory method)
(d3rlpy.models.optimizers.RMSpropFactory method)
(d3rlpy.models.optimizers.SGDFactory method)
create_continuous() (d3rlpy.models.q_functions.FQFQFunctionFactory method)
(d3rlpy.models.q_functions.IQNQFunctionFactory method)
(d3rlpy.models.q_functions.MeanQFunctionFactory method)
(d3rlpy.models.q_functions.QRQFunctionFactory method)
create_discrete() (d3rlpy.models.q_functions.FQFQFunctionFactory method)
(d3rlpy.models.q_functions.IQNQFunctionFactory method)
(d3rlpy.models.q_functions.MeanQFunctionFactory method)
(d3rlpy.models.q_functions.QRQFunctionFactory method)
create_impl() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
create_with_action() (d3rlpy.models.encoders.DefaultEncoderFactory method)
(d3rlpy.models.encoders.DenseEncoderFactory method)
(d3rlpy.models.encoders.PixelEncoderFactory method)
(d3rlpy.models.encoders.VectorEncoderFactory method)
CRR (class in d3rlpy.algos)
D
d3rlpy
module
d3rlpy.algos
module
d3rlpy.dataset
module
d3rlpy.datasets
module
d3rlpy.dynamics
module
d3rlpy.metrics
module
d3rlpy.models.encoders
module
d3rlpy.models.optimizers
module
d3rlpy.models.q_functions
module
d3rlpy.online
module
d3rlpy.ope
module
d3rlpy.preprocessing
module
DDPG (class in d3rlpy.algos)
DefaultEncoderFactory (class in d3rlpy.models.encoders)
DenseEncoderFactory (class in d3rlpy.models.encoders)
discounted_sum_of_advantage_scorer() (in module d3rlpy.metrics.scorer)
discrete_action_match_scorer() (in module d3rlpy.metrics.scorer)
DiscreteAWR (class in d3rlpy.algos)
DiscreteBC (class in d3rlpy.algos)
DiscreteBCQ (class in d3rlpy.algos)
DiscreteCQL (class in d3rlpy.algos)
DiscreteFQE (class in d3rlpy.ope)
DiscreteRandomPolicy (class in d3rlpy.algos)
DiscreteSAC (class in d3rlpy.algos)
DoubleDQN (class in d3rlpy.algos)
DQN (class in d3rlpy.algos)
dump() (d3rlpy.dataset.MDPDataset method)
dynamics_observation_prediction_error_scorer() (in module d3rlpy.metrics.scorer)
dynamics_prediction_variance_scorer() (in module d3rlpy.metrics.scorer)
dynamics_reward_prediction_error_scorer() (in module d3rlpy.metrics.scorer)
E
embed_size (d3rlpy.models.q_functions.FQFQFunctionFactory attribute)
(d3rlpy.models.q_functions.IQNQFunctionFactory attribute)
entropy_coeff (d3rlpy.models.q_functions.FQFQFunctionFactory attribute)
Episode (class in d3rlpy.dataset)
episode_terminals (d3rlpy.dataset.MDPDataset attribute)
episodes (d3rlpy.dataset.MDPDataset attribute)
evaluate_on_environment() (in module d3rlpy.metrics.scorer)
extend() (d3rlpy.dataset.MDPDataset method)
F
fit() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
(d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MinMaxScaler method)
(d3rlpy.preprocessing.PixelScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
(d3rlpy.preprocessing.StandardScaler method)
fit_batch_online() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
fit_online() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
fit_with_env() (d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MinMaxScaler method)
(d3rlpy.preprocessing.PixelScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
(d3rlpy.preprocessing.StandardScaler method)
fitter() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
FQE (class in d3rlpy.ope)
FQFQFunctionFactory (class in d3rlpy.models.q_functions)
from_json() (d3rlpy.algos.AWAC class method)
(d3rlpy.algos.AWR class method)
(d3rlpy.algos.BC class method)
(d3rlpy.algos.BCQ class method)
(d3rlpy.algos.BEAR class method)
(d3rlpy.algos.COMBO class method)
(d3rlpy.algos.CQL class method)
(d3rlpy.algos.CRR class method)
(d3rlpy.algos.DDPG class method)
(d3rlpy.algos.DiscreteAWR class method)
(d3rlpy.algos.DiscreteBC class method)
(d3rlpy.algos.DiscreteBCQ class method)
(d3rlpy.algos.DiscreteCQL class method)
(d3rlpy.algos.DiscreteRandomPolicy class method)
(d3rlpy.algos.DiscreteSAC class method)
(d3rlpy.algos.DoubleDQN class method)
(d3rlpy.algos.DQN class method)
(d3rlpy.algos.MOPO class method)
(d3rlpy.algos.PLAS class method)
(d3rlpy.algos.PLASWithPerturbation class method)
(d3rlpy.algos.RandomPolicy class method)
(d3rlpy.algos.SAC class method)
(d3rlpy.algos.TD3 class method)
(d3rlpy.algos.TD3PlusBC class method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics class method)
(d3rlpy.ope.DiscreteFQE class method)
(d3rlpy.ope.FQE class method)
G
gamma (d3rlpy.algos.AWAC attribute)
(d3rlpy.algos.AWR attribute)
(d3rlpy.algos.BC attribute)
(d3rlpy.algos.BCQ attribute)
(d3rlpy.algos.BEAR attribute)
(d3rlpy.algos.COMBO attribute)
(d3rlpy.algos.CQL attribute)
(d3rlpy.algos.CRR attribute)
(d3rlpy.algos.DDPG attribute)
(d3rlpy.algos.DiscreteAWR attribute)
(d3rlpy.algos.DiscreteBC attribute)
(d3rlpy.algos.DiscreteBCQ attribute)
(d3rlpy.algos.DiscreteCQL attribute)
(d3rlpy.algos.DiscreteRandomPolicy attribute)
(d3rlpy.algos.DiscreteSAC attribute)
(d3rlpy.algos.DoubleDQN attribute)
(d3rlpy.algos.DQN attribute)
(d3rlpy.algos.MOPO attribute)
(d3rlpy.algos.PLAS attribute)
(d3rlpy.algos.PLASWithPerturbation attribute)
(d3rlpy.algos.RandomPolicy attribute)
(d3rlpy.algos.SAC attribute)
(d3rlpy.algos.TD3 attribute)
(d3rlpy.algos.TD3PlusBC attribute)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics attribute)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
generate_new_data() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
get_action_size() (d3rlpy.dataset.Episode method)
(d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.Transition method)
get_action_type() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
get_additional_data() (d3rlpy.dataset.TransitionMiniBatch method)
get_atari() (in module d3rlpy.datasets)
get_cartpole() (in module d3rlpy.datasets)
get_d4rl() (in module d3rlpy.datasets)
get_dataset() (in module d3rlpy.datasets)
get_observation_shape() (d3rlpy.dataset.Episode method)
(d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.Transition method)
get_params() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.models.encoders.DefaultEncoderFactory method)
(d3rlpy.models.encoders.DenseEncoderFactory method)
(d3rlpy.models.encoders.PixelEncoderFactory method)
(d3rlpy.models.encoders.VectorEncoderFactory method)
(d3rlpy.models.optimizers.AdamFactory method)
(d3rlpy.models.optimizers.OptimizerFactory method)
(d3rlpy.models.optimizers.RMSpropFactory method)
(d3rlpy.models.optimizers.SGDFactory method)
(d3rlpy.models.q_functions.FQFQFunctionFactory method)
(d3rlpy.models.q_functions.IQNQFunctionFactory method)
(d3rlpy.models.q_functions.MeanQFunctionFactory method)
(d3rlpy.models.q_functions.QRQFunctionFactory method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
(d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MinMaxScaler method)
(d3rlpy.preprocessing.PixelScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
(d3rlpy.preprocessing.StandardScaler method)
get_pendulum() (in module d3rlpy.datasets)
get_pybullet() (in module d3rlpy.datasets)
get_type() (d3rlpy.models.encoders.DefaultEncoderFactory method)
(d3rlpy.models.encoders.DenseEncoderFactory method)
(d3rlpy.models.encoders.PixelEncoderFactory method)
(d3rlpy.models.encoders.VectorEncoderFactory method)
(d3rlpy.models.q_functions.FQFQFunctionFactory method)
(d3rlpy.models.q_functions.IQNQFunctionFactory method)
(d3rlpy.models.q_functions.MeanQFunctionFactory method)
(d3rlpy.models.q_functions.QRQFunctionFactory method)
(d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MinMaxScaler method)
(d3rlpy.preprocessing.PixelScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
(d3rlpy.preprocessing.StandardScaler method)
grad_step (d3rlpy.algos.AWAC attribute)
(d3rlpy.algos.AWR attribute)
(d3rlpy.algos.BC attribute)
(d3rlpy.algos.BCQ attribute)
(d3rlpy.algos.BEAR attribute)
(d3rlpy.algos.COMBO attribute)
(d3rlpy.algos.CQL attribute)
(d3rlpy.algos.CRR attribute)
(d3rlpy.algos.DDPG attribute)
(d3rlpy.algos.DiscreteAWR attribute)
(d3rlpy.algos.DiscreteBC attribute)
(d3rlpy.algos.DiscreteBCQ attribute)
(d3rlpy.algos.DiscreteCQL attribute)
(d3rlpy.algos.DiscreteRandomPolicy attribute)
(d3rlpy.algos.DiscreteSAC attribute)
(d3rlpy.algos.DoubleDQN attribute)
(d3rlpy.algos.DQN attribute)
(d3rlpy.algos.MOPO attribute)
(d3rlpy.algos.PLAS attribute)
(d3rlpy.algos.PLASWithPerturbation attribute)
(d3rlpy.algos.RandomPolicy attribute)
(d3rlpy.algos.SAC attribute)
(d3rlpy.algos.TD3 attribute)
(d3rlpy.algos.TD3PlusBC attribute)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics attribute)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
I
impl (d3rlpy.algos.AWAC attribute)
(d3rlpy.algos.AWR attribute)
(d3rlpy.algos.BC attribute)
(d3rlpy.algos.BCQ attribute)
(d3rlpy.algos.BEAR attribute)
(d3rlpy.algos.COMBO attribute)
(d3rlpy.algos.CQL attribute)
(d3rlpy.algos.CRR attribute)
(d3rlpy.algos.DDPG attribute)
(d3rlpy.algos.DiscreteAWR attribute)
(d3rlpy.algos.DiscreteBC attribute)
(d3rlpy.algos.DiscreteBCQ attribute)
(d3rlpy.algos.DiscreteCQL attribute)
(d3rlpy.algos.DiscreteRandomPolicy attribute)
(d3rlpy.algos.DiscreteSAC attribute)
(d3rlpy.algos.DoubleDQN attribute)
(d3rlpy.algos.DQN attribute)
(d3rlpy.algos.MOPO attribute)
(d3rlpy.algos.PLAS attribute)
(d3rlpy.algos.PLASWithPerturbation attribute)
(d3rlpy.algos.RandomPolicy attribute)
(d3rlpy.algos.SAC attribute)
(d3rlpy.algos.TD3 attribute)
(d3rlpy.algos.TD3PlusBC attribute)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics attribute)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
initial_state_value_estimation_scorer() (in module d3rlpy.metrics.scorer)
IQNQFunctionFactory (class in d3rlpy.models.q_functions)
is_action_discrete() (d3rlpy.dataset.MDPDataset method)
L
LinearDecayEpsilonGreedy (class in d3rlpy.online.explorers)
load() (d3rlpy.dataset.MDPDataset class method)
load_model() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
M
mask (d3rlpy.dataset.Transition attribute)
masks (d3rlpy.dataset.TransitionMiniBatch attribute)
MDPDataset (class in d3rlpy.dataset)
MeanQFunctionFactory (class in d3rlpy.models.q_functions)
MinMaxActionScaler (class in d3rlpy.preprocessing)
MinMaxRewardScaler (class in d3rlpy.preprocessing)
MinMaxScaler (class in d3rlpy.preprocessing)
module
d3rlpy
d3rlpy.algos
d3rlpy.dataset
d3rlpy.datasets
d3rlpy.dynamics
d3rlpy.metrics
d3rlpy.models.encoders
d3rlpy.models.optimizers
d3rlpy.models.q_functions
d3rlpy.online
d3rlpy.ope
d3rlpy.preprocessing
MOPO (class in d3rlpy.algos)
N
n_frames (d3rlpy.algos.AWAC attribute)
(d3rlpy.algos.AWR attribute)
(d3rlpy.algos.BC attribute)
(d3rlpy.algos.BCQ attribute)
(d3rlpy.algos.BEAR attribute)
(d3rlpy.algos.COMBO attribute)
(d3rlpy.algos.CQL attribute)
(d3rlpy.algos.CRR attribute)
(d3rlpy.algos.DDPG attribute)
(d3rlpy.algos.DiscreteAWR attribute)
(d3rlpy.algos.DiscreteBC attribute)
(d3rlpy.algos.DiscreteBCQ attribute)
(d3rlpy.algos.DiscreteCQL attribute)
(d3rlpy.algos.DiscreteRandomPolicy attribute)
(d3rlpy.algos.DiscreteSAC attribute)
(d3rlpy.algos.DoubleDQN attribute)
(d3rlpy.algos.DQN attribute)
(d3rlpy.algos.MOPO attribute)
(d3rlpy.algos.PLAS attribute)
(d3rlpy.algos.PLASWithPerturbation attribute)
(d3rlpy.algos.RandomPolicy attribute)
(d3rlpy.algos.SAC attribute)
(d3rlpy.algos.TD3 attribute)
(d3rlpy.algos.TD3PlusBC attribute)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics attribute)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
n_greedy_quantiles (d3rlpy.models.q_functions.IQNQFunctionFactory attribute)
n_quantiles (d3rlpy.models.q_functions.FQFQFunctionFactory attribute)
(d3rlpy.models.q_functions.IQNQFunctionFactory attribute)
(d3rlpy.models.q_functions.QRQFunctionFactory attribute)
n_steps (d3rlpy.algos.AWAC attribute)
(d3rlpy.algos.AWR attribute)
(d3rlpy.algos.BC attribute)
(d3rlpy.algos.BCQ attribute)
(d3rlpy.algos.BEAR attribute)
(d3rlpy.algos.COMBO attribute)
(d3rlpy.algos.CQL attribute)
(d3rlpy.algos.CRR attribute)
(d3rlpy.algos.DDPG attribute)
(d3rlpy.algos.DiscreteAWR attribute)
(d3rlpy.algos.DiscreteBC attribute)
(d3rlpy.algos.DiscreteBCQ attribute)
(d3rlpy.algos.DiscreteCQL attribute)
(d3rlpy.algos.DiscreteRandomPolicy attribute)
(d3rlpy.algos.DiscreteSAC attribute)
(d3rlpy.algos.DoubleDQN attribute)
(d3rlpy.algos.DQN attribute)
(d3rlpy.algos.MOPO attribute)
(d3rlpy.algos.PLAS attribute)
(d3rlpy.algos.PLASWithPerturbation attribute)
(d3rlpy.algos.RandomPolicy attribute)
(d3rlpy.algos.SAC attribute)
(d3rlpy.algos.TD3 attribute)
(d3rlpy.algos.TD3PlusBC attribute)
(d3rlpy.dataset.TransitionMiniBatch attribute)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics attribute)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
next_action (d3rlpy.dataset.Transition attribute)
next_actions (d3rlpy.dataset.TransitionMiniBatch attribute)
next_observation (d3rlpy.dataset.Transition attribute)
next_observations (d3rlpy.dataset.TransitionMiniBatch attribute)
next_reward (d3rlpy.dataset.Transition attribute)
next_rewards (d3rlpy.dataset.TransitionMiniBatch attribute)
next_transition (d3rlpy.dataset.Transition attribute)
NormalNoise (class in d3rlpy.online.explorers)
O
observation (d3rlpy.dataset.Transition attribute)
observation_shape (d3rlpy.algos.AWAC attribute)
(d3rlpy.algos.AWR attribute)
(d3rlpy.algos.BC attribute)
(d3rlpy.algos.BCQ attribute)
(d3rlpy.algos.BEAR attribute)
(d3rlpy.algos.COMBO attribute)
(d3rlpy.algos.CQL attribute)
(d3rlpy.algos.CRR attribute)
(d3rlpy.algos.DDPG attribute)
(d3rlpy.algos.DiscreteAWR attribute)
(d3rlpy.algos.DiscreteBC attribute)
(d3rlpy.algos.DiscreteBCQ attribute)
(d3rlpy.algos.DiscreteCQL attribute)
(d3rlpy.algos.DiscreteRandomPolicy attribute)
(d3rlpy.algos.DiscreteSAC attribute)
(d3rlpy.algos.DoubleDQN attribute)
(d3rlpy.algos.DQN attribute)
(d3rlpy.algos.MOPO attribute)
(d3rlpy.algos.PLAS attribute)
(d3rlpy.algos.PLASWithPerturbation attribute)
(d3rlpy.algos.RandomPolicy attribute)
(d3rlpy.algos.SAC attribute)
(d3rlpy.algos.TD3 attribute)
(d3rlpy.algos.TD3PlusBC attribute)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics attribute)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
observations (d3rlpy.dataset.Episode attribute)
(d3rlpy.dataset.MDPDataset attribute)
(d3rlpy.dataset.TransitionMiniBatch attribute)
OptimizerFactory (class in d3rlpy.models.optimizers)
P
PixelEncoderFactory (class in d3rlpy.models.encoders)
PixelScaler (class in d3rlpy.preprocessing)
PLAS (class in d3rlpy.algos)
PLASWithPerturbation (class in d3rlpy.algos)
predict() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
predict_value() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
prev_transition (d3rlpy.dataset.Transition attribute)
ProbabilisticEnsembleDynamics (class in d3rlpy.dynamics)
Q
QRQFunctionFactory (class in d3rlpy.models.q_functions)
R
RandomPolicy (class in d3rlpy.algos)
ReplayBuffer (class in d3rlpy.online.buffers)
reverse_transform() (d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MinMaxScaler method)
(d3rlpy.preprocessing.PixelScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
(d3rlpy.preprocessing.StandardScaler method)
reverse_transform_numpy() (d3rlpy.preprocessing.MinMaxActionScaler method)
reward (d3rlpy.dataset.Transition attribute)
reward_scaler (d3rlpy.algos.AWAC attribute)
(d3rlpy.algos.AWR attribute)
(d3rlpy.algos.BC attribute)
(d3rlpy.algos.BCQ attribute)
(d3rlpy.algos.BEAR attribute)
(d3rlpy.algos.COMBO attribute)
(d3rlpy.algos.CQL attribute)
(d3rlpy.algos.CRR attribute)
(d3rlpy.algos.DDPG attribute)
(d3rlpy.algos.DiscreteAWR attribute)
(d3rlpy.algos.DiscreteBC attribute)
(d3rlpy.algos.DiscreteBCQ attribute)
(d3rlpy.algos.DiscreteCQL attribute)
(d3rlpy.algos.DiscreteRandomPolicy attribute)
(d3rlpy.algos.DiscreteSAC attribute)
(d3rlpy.algos.DoubleDQN attribute)
(d3rlpy.algos.DQN attribute)
(d3rlpy.algos.MOPO attribute)
(d3rlpy.algos.PLAS attribute)
(d3rlpy.algos.PLASWithPerturbation attribute)
(d3rlpy.algos.RandomPolicy attribute)
(d3rlpy.algos.SAC attribute)
(d3rlpy.algos.TD3 attribute)
(d3rlpy.algos.TD3PlusBC attribute)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics attribute)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
rewards (d3rlpy.dataset.Episode attribute)
(d3rlpy.dataset.MDPDataset attribute)
(d3rlpy.dataset.TransitionMiniBatch attribute)
RMSpropFactory (class in d3rlpy.models.optimizers)
S
SAC (class in d3rlpy.algos)
sample() (d3rlpy.online.buffers.BatchReplayBuffer method)
(d3rlpy.online.buffers.ReplayBuffer method)
(d3rlpy.online.explorers.ConstantEpsilonGreedy method)
(d3rlpy.online.explorers.LinearDecayEpsilonGreedy method)
(d3rlpy.online.explorers.NormalNoise method)
sample_action() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
save_model() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
save_params() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
save_policy() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
scaler (d3rlpy.algos.AWAC attribute)
(d3rlpy.algos.AWR attribute)
(d3rlpy.algos.BC attribute)
(d3rlpy.algos.BCQ attribute)
(d3rlpy.algos.BEAR attribute)
(d3rlpy.algos.COMBO attribute)
(d3rlpy.algos.CQL attribute)
(d3rlpy.algos.CRR attribute)
(d3rlpy.algos.DDPG attribute)
(d3rlpy.algos.DiscreteAWR attribute)
(d3rlpy.algos.DiscreteBC attribute)
(d3rlpy.algos.DiscreteBCQ attribute)
(d3rlpy.algos.DiscreteCQL attribute)
(d3rlpy.algos.DiscreteRandomPolicy attribute)
(d3rlpy.algos.DiscreteSAC attribute)
(d3rlpy.algos.DoubleDQN attribute)
(d3rlpy.algos.DQN attribute)
(d3rlpy.algos.MOPO attribute)
(d3rlpy.algos.PLAS attribute)
(d3rlpy.algos.PLASWithPerturbation attribute)
(d3rlpy.algos.RandomPolicy attribute)
(d3rlpy.algos.SAC attribute)
(d3rlpy.algos.TD3 attribute)
(d3rlpy.algos.TD3PlusBC attribute)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics attribute)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
set_active_logger() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
set_grad_step() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
set_params() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
SGDFactory (class in d3rlpy.models.optimizers)
share_encoder (d3rlpy.models.q_functions.FQFQFunctionFactory attribute)
(d3rlpy.models.q_functions.IQNQFunctionFactory attribute)
(d3rlpy.models.q_functions.MeanQFunctionFactory attribute)
(d3rlpy.models.q_functions.QRQFunctionFactory attribute)
size() (d3rlpy.dataset.Episode method)
(d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.TransitionMiniBatch method)
(d3rlpy.online.buffers.BatchReplayBuffer method)
(d3rlpy.online.buffers.ReplayBuffer method)
soft_opc_scorer() (in module d3rlpy.metrics.scorer)
StandardRewardScaler (class in d3rlpy.preprocessing)
StandardScaler (class in d3rlpy.preprocessing)
T
TD3 (class in d3rlpy.algos)
TD3PlusBC (class in d3rlpy.algos)
td_error_scorer() (in module d3rlpy.metrics.scorer)
terminal (d3rlpy.dataset.Episode attribute)
(d3rlpy.dataset.Transition attribute)
terminals (d3rlpy.dataset.MDPDataset attribute)
(d3rlpy.dataset.TransitionMiniBatch attribute)
to_mdp_dataset() (d3rlpy.online.buffers.BatchReplayBuffer method)
(d3rlpy.online.buffers.ReplayBuffer method)
transform() (d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MinMaxScaler method)
(d3rlpy.preprocessing.PixelScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
(d3rlpy.preprocessing.StandardScaler method)
transform_numpy() (d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
Transition (class in d3rlpy.dataset)
TransitionMiniBatch (class in d3rlpy.dataset)
transitions (d3rlpy.dataset.Episode attribute)
(d3rlpy.dataset.TransitionMiniBatch attribute)
(d3rlpy.online.buffers.BatchReplayBuffer attribute)
(d3rlpy.online.buffers.ReplayBuffer attribute)
TYPE (d3rlpy.models.encoders.DefaultEncoderFactory attribute)
(d3rlpy.models.encoders.DenseEncoderFactory attribute)
(d3rlpy.models.encoders.PixelEncoderFactory attribute)
(d3rlpy.models.encoders.VectorEncoderFactory attribute)
(d3rlpy.models.q_functions.FQFQFunctionFactory attribute)
(d3rlpy.models.q_functions.IQNQFunctionFactory attribute)
(d3rlpy.models.q_functions.MeanQFunctionFactory attribute)
(d3rlpy.models.q_functions.QRQFunctionFactory attribute)
(d3rlpy.preprocessing.ClipRewardScaler attribute)
(d3rlpy.preprocessing.MinMaxActionScaler attribute)
(d3rlpy.preprocessing.MinMaxRewardScaler attribute)
(d3rlpy.preprocessing.MinMaxScaler attribute)
(d3rlpy.preprocessing.PixelScaler attribute)
(d3rlpy.preprocessing.StandardRewardScaler attribute)
(d3rlpy.preprocessing.StandardScaler attribute)
U
update() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.AWR method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.COMBO method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DiscreteAWR method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DoubleDQN method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.MOPO method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.PLASWithPerturbation method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.dynamics.ProbabilisticEnsembleDynamics method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
V
value_estimation_std_scorer() (in module d3rlpy.metrics.scorer)
VectorEncoderFactory (class in d3rlpy.models.encoders)
Read the Docs
v: v0.91
Versions
latest
stable
v0.91
v0.90
v0.80
v0.70
v0.61
v0.60
v0.51
v0.50
v0.41
v0.40
v0.32
v0.31
v0.30
v0.23
v0.22
v0.21
v0.2
v0.1
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds