d3rlpy
v2.2.0
Tutorials
Tutorials
Jupyter Notebooks
References
Software Design
API Reference
Command Line Interface
Installation
Tips
Other
Paper Reproductions
License
d3rlpy
»
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
_
__call__() (d3rlpy.algos.GreedyTransformerActionSampler method)
(d3rlpy.algos.IdentityTransformerActionSampler method)
(d3rlpy.algos.SoftmaxTransformerActionSampler method)
(d3rlpy.algos.TransformerActionSampler method)
(d3rlpy.dataset.BasicTrajectorySlicer method)
(d3rlpy.dataset.BasicTransitionPicker method)
(d3rlpy.dataset.FrameStackTrajectorySlicer method)
(d3rlpy.dataset.FrameStackTransitionPicker method)
(d3rlpy.dataset.MultiStepTransitionPicker method)
(d3rlpy.dataset.TrajectorySlicerProtocol method)
(d3rlpy.dataset.TransitionPickerProtocol method)
(d3rlpy.metrics.AverageValueEstimationEvaluator method)
(d3rlpy.metrics.CompareContinuousActionDiffEvaluator method)
(d3rlpy.metrics.CompareDiscreteActionMatchEvaluator method)
(d3rlpy.metrics.ContinuousActionDiffEvaluator method)
(d3rlpy.metrics.DiscountedSumOfAdvantageEvaluator method)
(d3rlpy.metrics.DiscreteActionMatchEvaluator method)
(d3rlpy.metrics.EnvironmentEvaluator method)
(d3rlpy.metrics.InitialStateValueEstimationEvaluator method)
(d3rlpy.metrics.SoftOPCEvaluator method)
(d3rlpy.metrics.TDErrorEvaluator method)
__getitem__() (d3rlpy.dataset.BufferProtocol method)
(d3rlpy.dataset.FIFOBuffer method)
(d3rlpy.dataset.InfiniteBuffer method)
__len__() (d3rlpy.dataset.FIFOBuffer method)
(d3rlpy.dataset.InfiniteBuffer method)
A
action_scaler (d3rlpy.base.LearnableBase property)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
action_size (d3rlpy.base.LearnableBase property)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
activation (d3rlpy.models.DefaultEncoderFactory attribute)
(d3rlpy.models.PixelEncoderFactory attribute)
(d3rlpy.models.VectorEncoderFactory attribute)
AdamFactory (class in d3rlpy.models)
after_write_metric() (d3rlpy.logging.CombineAdapter method)
(d3rlpy.logging.FileAdapter method)
(d3rlpy.logging.LoggerAdapter method)
(d3rlpy.logging.NoopAdapter method)
(d3rlpy.logging.TensorboardAdapter method)
algo (d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
alpha (d3rlpy.models.RMSpropFactory attribute)
amsgrad (d3rlpy.models.AdamFactory attribute)
(d3rlpy.models.GPTAdamWFactory attribute)
append() (d3rlpy.dataset.BufferProtocol method)
(d3rlpy.dataset.FIFOBuffer method)
(d3rlpy.dataset.InfiniteBuffer method)
(d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.ReplayBuffer method)
append_episode() (d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.ReplayBuffer method)
as_stateful_wrapper() (d3rlpy.algos.TransformerAlgoBase method)
AverageValueEstimationEvaluator (class in d3rlpy.metrics)
AWAC (class in d3rlpy.algos)
AWACConfig (class in d3rlpy.algos)
B
BasicTrajectorySlicer (class in d3rlpy.dataset)
BasicTransitionPicker (class in d3rlpy.dataset)
BasicWriterPreprocess (class in d3rlpy.dataset)
batch_size (d3rlpy.base.LearnableBase property)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
BC (class in d3rlpy.algos)
BCConfig (class in d3rlpy.algos)
BCQ (class in d3rlpy.algos)
BCQConfig (class in d3rlpy.algos)
BEAR (class in d3rlpy.algos)
BEARConfig (class in d3rlpy.algos)
before_write_metric() (d3rlpy.logging.CombineAdapter method)
(d3rlpy.logging.FileAdapter method)
(d3rlpy.logging.LoggerAdapter method)
(d3rlpy.logging.NoopAdapter method)
(d3rlpy.logging.TensorboardAdapter method)
betas (d3rlpy.models.AdamFactory attribute)
(d3rlpy.models.GPTAdamWFactory attribute)
buffer (d3rlpy.dataset.MDPDataset attribute)
(d3rlpy.dataset.ReplayBuffer attribute)
BufferProtocol (class in d3rlpy.dataset)
build_with_dataset() (d3rlpy.base.LearnableBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
build_with_env() (d3rlpy.base.LearnableBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
built (d3rlpy.preprocessing.ClipRewardScaler attribute)
(d3rlpy.preprocessing.ConstantShiftRewardScaler attribute)
(d3rlpy.preprocessing.MinMaxActionScaler attribute)
(d3rlpy.preprocessing.MinMaxObservationScaler attribute)
(d3rlpy.preprocessing.MinMaxRewardScaler attribute)
(d3rlpy.preprocessing.MultiplyRewardScaler attribute)
(d3rlpy.preprocessing.PixelObservationScaler attribute)
(d3rlpy.preprocessing.ReturnBasedRewardScaler attribute)
(d3rlpy.preprocessing.StandardObservationScaler attribute)
(d3rlpy.preprocessing.StandardRewardScaler attribute)
C
centered (d3rlpy.models.RMSpropFactory attribute)
clip_episode() (d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.ReplayBuffer method)
ClipRewardScaler (class in d3rlpy.preprocessing)
close() (d3rlpy.logging.CombineAdapter method)
(d3rlpy.logging.FileAdapter method)
(d3rlpy.logging.LoggerAdapter method)
(d3rlpy.logging.NoopAdapter method)
(d3rlpy.logging.TensorboardAdapter method)
collect() (d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
CombineAdapter (class in d3rlpy.logging)
CombineAdapterFactory (class in d3rlpy.logging)
CompareContinuousActionDiffEvaluator (class in d3rlpy.metrics)
CompareDiscreteActionMatchEvaluator (class in d3rlpy.metrics)
compute_epsilon() (d3rlpy.algos.LinearDecayEpsilonGreedy method)
config (d3rlpy.base.LearnableBase property)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
ConstantEpsilonGreedy (class in d3rlpy.algos)
ConstantShiftRewardScaler (class in d3rlpy.preprocessing)
ContinuousActionDiffEvaluator (class in d3rlpy.metrics)
copy_policy_from() (d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
copy_policy_optim_from() (d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
copy_q_function_from() (d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
copy_q_function_optim_from() (d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
CQL (class in d3rlpy.algos)
CQLConfig (class in d3rlpy.algos)
create() (d3rlpy.algos.AWACConfig method)
(d3rlpy.algos.BCConfig method)
(d3rlpy.algos.BCQConfig method)
(d3rlpy.algos.BEARConfig method)
(d3rlpy.algos.CQLConfig method)
(d3rlpy.algos.CRRConfig method)
(d3rlpy.algos.DDPGConfig method)
(d3rlpy.algos.DecisionTransformerConfig method)
(d3rlpy.algos.DiscreteBCConfig method)
(d3rlpy.algos.DiscreteBCQConfig method)
(d3rlpy.algos.DiscreteCQLConfig method)
(d3rlpy.algos.DiscreteDecisionTransformerConfig method)
(d3rlpy.algos.DiscreteRandomPolicyConfig method)
(d3rlpy.algos.DiscreteSACConfig method)
(d3rlpy.algos.DoubleDQNConfig method)
(d3rlpy.algos.DQNConfig method)
(d3rlpy.algos.IQLConfig method)
(d3rlpy.algos.NFQConfig method)
(d3rlpy.algos.PLASConfig method)
(d3rlpy.algos.PLASWithPerturbationConfig method)
(d3rlpy.algos.RandomPolicyConfig method)
(d3rlpy.algos.SACConfig method)
(d3rlpy.algos.TD3Config method)
(d3rlpy.algos.TD3PlusBCConfig method)
(d3rlpy.logging.CombineAdapterFactory method)
(d3rlpy.logging.FileAdapterFactory method)
(d3rlpy.logging.LoggerAdapterFactory method)
(d3rlpy.logging.NoopAdapterFactory method)
(d3rlpy.logging.TensorboardAdapterFactory method)
(d3rlpy.models.AdamFactory method)
(d3rlpy.models.DefaultEncoderFactory method)
(d3rlpy.models.GPTAdamWFactory method)
(d3rlpy.models.OptimizerFactory method)
(d3rlpy.models.PixelEncoderFactory method)
(d3rlpy.models.RMSpropFactory method)
(d3rlpy.models.SGDFactory method)
(d3rlpy.models.VectorEncoderFactory method)
create_continuous() (d3rlpy.models.IQNQFunctionFactory method)
(d3rlpy.models.MeanQFunctionFactory method)
(d3rlpy.models.QRQFunctionFactory method)
create_discrete() (d3rlpy.models.IQNQFunctionFactory method)
(d3rlpy.models.MeanQFunctionFactory method)
(d3rlpy.models.QRQFunctionFactory method)
create_fifo_replay_buffer() (in module d3rlpy.dataset)
create_impl() (d3rlpy.base.LearnableBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
create_infinite_replay_buffer() (in module d3rlpy.dataset)
create_with_action() (d3rlpy.models.DefaultEncoderFactory method)
(d3rlpy.models.PixelEncoderFactory method)
(d3rlpy.models.VectorEncoderFactory method)
CRR (class in d3rlpy.algos)
CRRConfig (class in d3rlpy.algos)
D
d3rlpy
module
d3rlpy.algos
module
,
[1]
d3rlpy.dataset
module
d3rlpy.datasets
module
d3rlpy.logging
module
d3rlpy.metrics
module
d3rlpy.models
module
,
[1]
,
[2]
d3rlpy.ope
module
d3rlpy.preprocessing
module
dampening (d3rlpy.models.SGDFactory attribute)
dataset_info (d3rlpy.dataset.MDPDataset attribute)
(d3rlpy.dataset.ReplayBuffer attribute)
DDPG (class in d3rlpy.algos)
DDPGConfig (class in d3rlpy.algos)
DecisionTransformer (class in d3rlpy.algos)
DecisionTransformerConfig (class in d3rlpy.algos)
DefaultEncoderFactory (class in d3rlpy.models)
deserialize() (d3rlpy.models.AdamFactory class method)
(d3rlpy.models.DefaultEncoderFactory class method)
(d3rlpy.models.GPTAdamWFactory class method)
(d3rlpy.models.IQNQFunctionFactory class method)
(d3rlpy.models.MeanQFunctionFactory class method)
(d3rlpy.models.OptimizerFactory class method)
(d3rlpy.models.PixelEncoderFactory class method)
(d3rlpy.models.QRQFunctionFactory class method)
(d3rlpy.models.RMSpropFactory class method)
(d3rlpy.models.SGDFactory class method)
(d3rlpy.models.VectorEncoderFactory class method)
(d3rlpy.preprocessing.ClipRewardScaler class method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler class method)
(d3rlpy.preprocessing.MinMaxActionScaler class method)
(d3rlpy.preprocessing.MinMaxObservationScaler class method)
(d3rlpy.preprocessing.MinMaxRewardScaler class method)
(d3rlpy.preprocessing.MultiplyRewardScaler class method)
(d3rlpy.preprocessing.PixelObservationScaler class method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler class method)
(d3rlpy.preprocessing.StandardObservationScaler class method)
(d3rlpy.preprocessing.StandardRewardScaler class method)
deserialize_from_dict() (d3rlpy.models.AdamFactory class method)
(d3rlpy.models.DefaultEncoderFactory class method)
(d3rlpy.models.GPTAdamWFactory class method)
(d3rlpy.models.IQNQFunctionFactory class method)
(d3rlpy.models.MeanQFunctionFactory class method)
(d3rlpy.models.OptimizerFactory class method)
(d3rlpy.models.PixelEncoderFactory class method)
(d3rlpy.models.QRQFunctionFactory class method)
(d3rlpy.models.RMSpropFactory class method)
(d3rlpy.models.SGDFactory class method)
(d3rlpy.models.VectorEncoderFactory class method)
(d3rlpy.preprocessing.ClipRewardScaler class method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler class method)
(d3rlpy.preprocessing.MinMaxActionScaler class method)
(d3rlpy.preprocessing.MinMaxObservationScaler class method)
(d3rlpy.preprocessing.MinMaxRewardScaler class method)
(d3rlpy.preprocessing.MultiplyRewardScaler class method)
(d3rlpy.preprocessing.PixelObservationScaler class method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler class method)
(d3rlpy.preprocessing.StandardObservationScaler class method)
(d3rlpy.preprocessing.StandardRewardScaler class method)
deserialize_from_file() (d3rlpy.models.AdamFactory class method)
(d3rlpy.models.DefaultEncoderFactory class method)
(d3rlpy.models.GPTAdamWFactory class method)
(d3rlpy.models.IQNQFunctionFactory class method)
(d3rlpy.models.MeanQFunctionFactory class method)
(d3rlpy.models.OptimizerFactory class method)
(d3rlpy.models.PixelEncoderFactory class method)
(d3rlpy.models.QRQFunctionFactory class method)
(d3rlpy.models.RMSpropFactory class method)
(d3rlpy.models.SGDFactory class method)
(d3rlpy.models.VectorEncoderFactory class method)
(d3rlpy.preprocessing.ClipRewardScaler class method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler class method)
(d3rlpy.preprocessing.MinMaxActionScaler class method)
(d3rlpy.preprocessing.MinMaxObservationScaler class method)
(d3rlpy.preprocessing.MinMaxRewardScaler class method)
(d3rlpy.preprocessing.MultiplyRewardScaler class method)
(d3rlpy.preprocessing.PixelObservationScaler class method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler class method)
(d3rlpy.preprocessing.StandardObservationScaler class method)
(d3rlpy.preprocessing.StandardRewardScaler class method)
DiscountedSumOfAdvantageEvaluator (class in d3rlpy.metrics)
DiscreteActionMatchEvaluator (class in d3rlpy.metrics)
DiscreteBC (class in d3rlpy.algos)
DiscreteBCConfig (class in d3rlpy.algos)
DiscreteBCQ (class in d3rlpy.algos)
DiscreteBCQConfig (class in d3rlpy.algos)
DiscreteCQL (class in d3rlpy.algos)
DiscreteCQLConfig (class in d3rlpy.algos)
DiscreteDecisionTransformer (class in d3rlpy.algos)
DiscreteDecisionTransformerConfig (class in d3rlpy.algos)
DiscreteFQE (class in d3rlpy.ope)
DiscreteRandomPolicy (class in d3rlpy.algos)
DiscreteRandomPolicyConfig (class in d3rlpy.algos)
DiscreteSAC (class in d3rlpy.algos)
DiscreteSACConfig (class in d3rlpy.algos)
DoubleDQN (class in d3rlpy.algos)
DoubleDQNConfig (class in d3rlpy.algos)
DQN (class in d3rlpy.algos)
DQNConfig (class in d3rlpy.algos)
dropout_rate (d3rlpy.models.DefaultEncoderFactory attribute)
(d3rlpy.models.PixelEncoderFactory attribute)
(d3rlpy.models.VectorEncoderFactory attribute)
dump() (d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.ReplayBuffer method)
E
embed_size (d3rlpy.models.IQNQFunctionFactory attribute)
EnvironmentEvaluator (class in d3rlpy.metrics)
episodes (d3rlpy.dataset.BufferProtocol attribute)
(d3rlpy.dataset.FIFOBuffer attribute)
(d3rlpy.dataset.InfiniteBuffer attribute)
(d3rlpy.dataset.MDPDataset attribute)
(d3rlpy.dataset.ReplayBuffer attribute)
eps (d3rlpy.models.AdamFactory attribute)
(d3rlpy.models.GPTAdamWFactory attribute)
(d3rlpy.models.RMSpropFactory attribute)
(d3rlpy.preprocessing.StandardObservationScaler attribute)
(d3rlpy.preprocessing.StandardRewardScaler attribute)
exclude_last_activation (d3rlpy.models.PixelEncoderFactory attribute)
(d3rlpy.models.VectorEncoderFactory attribute)
F
feature_size (d3rlpy.models.PixelEncoderFactory attribute)
FIFOBuffer (class in d3rlpy.dataset)
FileAdapter (class in d3rlpy.logging)
FileAdapterFactory (class in d3rlpy.logging)
fit() (d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.algos.TransformerAlgoBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
fit_online() (d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
fit_with_env() (d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxObservationScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MultiplyRewardScaler method)
(d3rlpy.preprocessing.PixelObservationScaler method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler method)
(d3rlpy.preprocessing.StandardObservationScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
fit_with_trajectory_slicer() (d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxObservationScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MultiplyRewardScaler method)
(d3rlpy.preprocessing.PixelObservationScaler method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler method)
(d3rlpy.preprocessing.StandardObservationScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
fit_with_transition_picker() (d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxObservationScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MultiplyRewardScaler method)
(d3rlpy.preprocessing.PixelObservationScaler method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler method)
(d3rlpy.preprocessing.StandardObservationScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
fitter() (d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
FQE (class in d3rlpy.ope)
FrameStackTrajectorySlicer (class in d3rlpy.dataset)
FrameStackTransitionPicker (class in d3rlpy.dataset)
from_dict() (d3rlpy.models.AdamFactory class method)
(d3rlpy.models.DefaultEncoderFactory class method)
(d3rlpy.models.GPTAdamWFactory class method)
(d3rlpy.models.IQNQFunctionFactory class method)
(d3rlpy.models.MeanQFunctionFactory class method)
(d3rlpy.models.OptimizerFactory class method)
(d3rlpy.models.PixelEncoderFactory class method)
(d3rlpy.models.QRQFunctionFactory class method)
(d3rlpy.models.RMSpropFactory class method)
(d3rlpy.models.SGDFactory class method)
(d3rlpy.models.VectorEncoderFactory class method)
(d3rlpy.preprocessing.ClipRewardScaler class method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler class method)
(d3rlpy.preprocessing.MinMaxActionScaler class method)
(d3rlpy.preprocessing.MinMaxObservationScaler class method)
(d3rlpy.preprocessing.MinMaxRewardScaler class method)
(d3rlpy.preprocessing.MultiplyRewardScaler class method)
(d3rlpy.preprocessing.PixelObservationScaler class method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler class method)
(d3rlpy.preprocessing.StandardObservationScaler class method)
(d3rlpy.preprocessing.StandardRewardScaler class method)
from_episode_generator() (d3rlpy.dataset.MDPDataset class method)
(d3rlpy.dataset.ReplayBuffer class method)
from_json() (d3rlpy.base.LearnableBase class method)
(d3rlpy.models.AdamFactory class method)
(d3rlpy.models.DefaultEncoderFactory class method)
(d3rlpy.models.GPTAdamWFactory class method)
(d3rlpy.models.IQNQFunctionFactory class method)
(d3rlpy.models.MeanQFunctionFactory class method)
(d3rlpy.models.OptimizerFactory class method)
(d3rlpy.models.PixelEncoderFactory class method)
(d3rlpy.models.QRQFunctionFactory class method)
(d3rlpy.models.RMSpropFactory class method)
(d3rlpy.models.SGDFactory class method)
(d3rlpy.models.VectorEncoderFactory class method)
(d3rlpy.ope.DiscreteFQE class method)
(d3rlpy.ope.FQE class method)
(d3rlpy.preprocessing.ClipRewardScaler class method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler class method)
(d3rlpy.preprocessing.MinMaxActionScaler class method)
(d3rlpy.preprocessing.MinMaxObservationScaler class method)
(d3rlpy.preprocessing.MinMaxRewardScaler class method)
(d3rlpy.preprocessing.MultiplyRewardScaler class method)
(d3rlpy.preprocessing.PixelObservationScaler class method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler class method)
(d3rlpy.preprocessing.StandardObservationScaler class method)
(d3rlpy.preprocessing.StandardRewardScaler class method)
G
gamma (d3rlpy.base.LearnableBase property)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
get_action_type() (d3rlpy.algos.AWAC method)
(d3rlpy.algos.BC method)
(d3rlpy.algos.BCQ method)
(d3rlpy.algos.BEAR method)
(d3rlpy.algos.CQL method)
(d3rlpy.algos.CRR method)
(d3rlpy.algos.DDPG method)
(d3rlpy.algos.DecisionTransformer method)
(d3rlpy.algos.DiscreteBC method)
(d3rlpy.algos.DiscreteBCQ method)
(d3rlpy.algos.DiscreteCQL method)
(d3rlpy.algos.DiscreteDecisionTransformer method)
(d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.DiscreteSAC method)
(d3rlpy.algos.DQN method)
(d3rlpy.algos.IQL method)
(d3rlpy.algos.NFQ method)
(d3rlpy.algos.PLAS method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.SAC method)
(d3rlpy.algos.TD3 method)
(d3rlpy.algos.TD3PlusBC method)
(d3rlpy.base.LearnableBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
get_atari() (in module d3rlpy.datasets)
get_atari_transitions() (in module d3rlpy.datasets)
get_cartpole() (in module d3rlpy.datasets)
get_d4rl() (in module d3rlpy.datasets)
get_dataset() (in module d3rlpy.datasets)
get_pendulum() (in module d3rlpy.datasets)
get_type() (d3rlpy.models.AdamFactory static method)
(d3rlpy.models.DefaultEncoderFactory static method)
(d3rlpy.models.GPTAdamWFactory static method)
(d3rlpy.models.IQNQFunctionFactory static method)
(d3rlpy.models.MeanQFunctionFactory static method)
(d3rlpy.models.OptimizerFactory static method)
(d3rlpy.models.PixelEncoderFactory static method)
(d3rlpy.models.QRQFunctionFactory static method)
(d3rlpy.models.RMSpropFactory static method)
(d3rlpy.models.SGDFactory static method)
(d3rlpy.models.VectorEncoderFactory static method)
(d3rlpy.preprocessing.ClipRewardScaler static method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler static method)
(d3rlpy.preprocessing.MinMaxActionScaler static method)
(d3rlpy.preprocessing.MinMaxObservationScaler static method)
(d3rlpy.preprocessing.MinMaxRewardScaler static method)
(d3rlpy.preprocessing.MultiplyRewardScaler static method)
(d3rlpy.preprocessing.PixelObservationScaler static method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler static method)
(d3rlpy.preprocessing.StandardObservationScaler static method)
(d3rlpy.preprocessing.StandardRewardScaler static method)
GPTAdamWFactory (class in d3rlpy.models)
grad_step (d3rlpy.base.LearnableBase property)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
GreedyTransformerActionSampler (class in d3rlpy.algos)
H
high (d3rlpy.preprocessing.ClipRewardScaler attribute)
I
IdentityTransformerActionSampler (class in d3rlpy.algos)
impl (d3rlpy.base.LearnableBase property)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
InfiniteBuffer (class in d3rlpy.dataset)
InitialStateValueEstimationEvaluator (class in d3rlpy.metrics)
inner_create_impl() (d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
IQL (class in d3rlpy.algos)
IQLConfig (class in d3rlpy.algos)
IQNQFunctionFactory (class in d3rlpy.models)
L
LastFrameWriterPreprocess (class in d3rlpy.dataset)
LearnableBase (class in d3rlpy.base)
LinearDecayEpsilonGreedy (class in d3rlpy.algos)
load() (d3rlpy.dataset.MDPDataset class method)
(d3rlpy.dataset.ReplayBuffer class method)
load_model() (d3rlpy.base.LearnableBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
logdir (d3rlpy.logging.FileAdapter attribute)
LoggerAdapter (class in d3rlpy.logging)
LoggerAdapterFactory (class in d3rlpy.logging)
low (d3rlpy.preprocessing.ClipRewardScaler attribute)
M
maximum (d3rlpy.preprocessing.MinMaxActionScaler attribute)
(d3rlpy.preprocessing.MinMaxObservationScaler attribute)
(d3rlpy.preprocessing.MinMaxRewardScaler attribute)
MDPDataset (class in d3rlpy.dataset)
mean (d3rlpy.preprocessing.StandardObservationScaler attribute)
(d3rlpy.preprocessing.StandardRewardScaler attribute)
MeanQFunctionFactory (class in d3rlpy.models)
minimum (d3rlpy.preprocessing.MinMaxActionScaler attribute)
(d3rlpy.preprocessing.MinMaxObservationScaler attribute)
(d3rlpy.preprocessing.MinMaxRewardScaler attribute)
MinMaxActionScaler (class in d3rlpy.preprocessing)
MinMaxObservationScaler (class in d3rlpy.preprocessing)
MinMaxRewardScaler (class in d3rlpy.preprocessing)
module
d3rlpy
d3rlpy.algos
,
[1]
d3rlpy.dataset
d3rlpy.datasets
d3rlpy.logging
d3rlpy.metrics
d3rlpy.models
,
[1]
,
[2]
d3rlpy.ope
d3rlpy.preprocessing
momentum (d3rlpy.models.RMSpropFactory attribute)
(d3rlpy.models.SGDFactory attribute)
multiplier (d3rlpy.preprocessing.ClipRewardScaler attribute)
(d3rlpy.preprocessing.MinMaxRewardScaler attribute)
(d3rlpy.preprocessing.MultiplyRewardScaler attribute)
(d3rlpy.preprocessing.ReturnBasedRewardScaler attribute)
(d3rlpy.preprocessing.StandardRewardScaler attribute)
MultiplyRewardScaler (class in d3rlpy.preprocessing)
MultiStepTransitionPicker (class in d3rlpy.dataset)
N
n_greedy_quantiles (d3rlpy.models.IQNQFunctionFactory attribute)
n_quantiles (d3rlpy.models.IQNQFunctionFactory attribute)
(d3rlpy.models.QRQFunctionFactory attribute)
nesterov (d3rlpy.models.SGDFactory attribute)
NFQ (class in d3rlpy.algos)
NFQConfig (class in d3rlpy.algos)
NoopAdapter (class in d3rlpy.logging)
NoopAdapterFactory (class in d3rlpy.logging)
NormalNoise (class in d3rlpy.algos)
O
observation_scaler (d3rlpy.base.LearnableBase property)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
observation_shape (d3rlpy.base.LearnableBase property)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
OptimizerFactory (class in d3rlpy.models)
P
PixelEncoderFactory (class in d3rlpy.models)
PixelObservationScaler (class in d3rlpy.preprocessing)
PLAS (class in d3rlpy.algos)
PLASConfig (class in d3rlpy.algos)
PLASWithPerturbation (class in d3rlpy.algos)
PLASWithPerturbationConfig (class in d3rlpy.algos)
predict() (d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.algos.TransformerAlgoBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
predict_value() (d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
process_action() (d3rlpy.dataset.BasicWriterPreprocess method)
(d3rlpy.dataset.LastFrameWriterPreprocess method)
(d3rlpy.dataset.WriterPreprocessProtocol method)
process_observation() (d3rlpy.dataset.BasicWriterPreprocess method)
(d3rlpy.dataset.LastFrameWriterPreprocess method)
(d3rlpy.dataset.WriterPreprocessProtocol method)
process_reward() (d3rlpy.dataset.BasicWriterPreprocess method)
(d3rlpy.dataset.LastFrameWriterPreprocess method)
(d3rlpy.dataset.WriterPreprocessProtocol method)
Q
QLearningAlgoBase (class in d3rlpy.algos)
QRQFunctionFactory (class in d3rlpy.models)
R
RandomPolicy (class in d3rlpy.algos)
RandomPolicyConfig (class in d3rlpy.algos)
ReplayBuffer (class in d3rlpy.dataset)
reset_optimizer_states() (d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
return_max (d3rlpy.preprocessing.ReturnBasedRewardScaler attribute)
return_min (d3rlpy.preprocessing.ReturnBasedRewardScaler attribute)
ReturnBasedRewardScaler (class in d3rlpy.preprocessing)
reverse_transform() (d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxObservationScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MultiplyRewardScaler method)
(d3rlpy.preprocessing.PixelObservationScaler method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler method)
(d3rlpy.preprocessing.StandardObservationScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
reverse_transform_numpy() (d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxObservationScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MultiplyRewardScaler method)
(d3rlpy.preprocessing.PixelObservationScaler method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler method)
(d3rlpy.preprocessing.StandardObservationScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
reward_scaler (d3rlpy.base.LearnableBase property)
(d3rlpy.ope.DiscreteFQE attribute)
(d3rlpy.ope.FQE attribute)
RMSpropFactory (class in d3rlpy.models)
S
SAC (class in d3rlpy.algos)
SACConfig (class in d3rlpy.algos)
sample() (d3rlpy.algos.ConstantEpsilonGreedy method)
(d3rlpy.algos.LinearDecayEpsilonGreedy method)
(d3rlpy.algos.NormalNoise method)
sample_action() (d3rlpy.algos.DiscreteRandomPolicy method)
(d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.algos.RandomPolicy method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
sample_trajectory() (d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.ReplayBuffer method)
sample_trajectory_batch() (d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.ReplayBuffer method)
sample_transition() (d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.ReplayBuffer method)
sample_transition_batch() (d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.ReplayBuffer method)
save() (d3rlpy.base.LearnableBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
save_model() (d3rlpy.base.LearnableBase method)
(d3rlpy.logging.CombineAdapter method)
(d3rlpy.logging.FileAdapter method)
(d3rlpy.logging.LoggerAdapter method)
(d3rlpy.logging.NoopAdapter method)
(d3rlpy.logging.TensorboardAdapter method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
save_policy() (d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
schema() (d3rlpy.models.AdamFactory class method)
(d3rlpy.models.DefaultEncoderFactory class method)
(d3rlpy.models.GPTAdamWFactory class method)
(d3rlpy.models.IQNQFunctionFactory class method)
(d3rlpy.models.MeanQFunctionFactory class method)
(d3rlpy.models.OptimizerFactory class method)
(d3rlpy.models.PixelEncoderFactory class method)
(d3rlpy.models.QRQFunctionFactory class method)
(d3rlpy.models.RMSpropFactory class method)
(d3rlpy.models.SGDFactory class method)
(d3rlpy.models.VectorEncoderFactory class method)
(d3rlpy.preprocessing.ClipRewardScaler class method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler class method)
(d3rlpy.preprocessing.MinMaxActionScaler class method)
(d3rlpy.preprocessing.MinMaxObservationScaler class method)
(d3rlpy.preprocessing.MinMaxRewardScaler class method)
(d3rlpy.preprocessing.MultiplyRewardScaler class method)
(d3rlpy.preprocessing.PixelObservationScaler class method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler class method)
(d3rlpy.preprocessing.StandardObservationScaler class method)
(d3rlpy.preprocessing.StandardRewardScaler class method)
serialize() (d3rlpy.models.AdamFactory method)
(d3rlpy.models.DefaultEncoderFactory method)
(d3rlpy.models.GPTAdamWFactory method)
(d3rlpy.models.IQNQFunctionFactory method)
(d3rlpy.models.MeanQFunctionFactory method)
(d3rlpy.models.OptimizerFactory method)
(d3rlpy.models.PixelEncoderFactory method)
(d3rlpy.models.QRQFunctionFactory method)
(d3rlpy.models.RMSpropFactory method)
(d3rlpy.models.SGDFactory method)
(d3rlpy.models.VectorEncoderFactory method)
(d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxObservationScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MultiplyRewardScaler method)
(d3rlpy.preprocessing.PixelObservationScaler method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler method)
(d3rlpy.preprocessing.StandardObservationScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
serialize_to_dict() (d3rlpy.models.AdamFactory method)
(d3rlpy.models.DefaultEncoderFactory method)
(d3rlpy.models.GPTAdamWFactory method)
(d3rlpy.models.IQNQFunctionFactory method)
(d3rlpy.models.MeanQFunctionFactory method)
(d3rlpy.models.OptimizerFactory method)
(d3rlpy.models.PixelEncoderFactory method)
(d3rlpy.models.QRQFunctionFactory method)
(d3rlpy.models.RMSpropFactory method)
(d3rlpy.models.SGDFactory method)
(d3rlpy.models.VectorEncoderFactory method)
(d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxObservationScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MultiplyRewardScaler method)
(d3rlpy.preprocessing.PixelObservationScaler method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler method)
(d3rlpy.preprocessing.StandardObservationScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
set_grad_step() (d3rlpy.base.LearnableBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
SGDFactory (class in d3rlpy.models)
share_encoder (d3rlpy.models.IQNQFunctionFactory attribute)
(d3rlpy.models.MeanQFunctionFactory attribute)
(d3rlpy.models.QRQFunctionFactory attribute)
size() (d3rlpy.dataset.MDPDataset method)
(d3rlpy.dataset.ReplayBuffer method)
SoftmaxTransformerActionSampler (class in d3rlpy.algos)
SoftOPCEvaluator (class in d3rlpy.metrics)
StandardObservationScaler (class in d3rlpy.preprocessing)
StandardRewardScaler (class in d3rlpy.preprocessing)
std (d3rlpy.preprocessing.StandardObservationScaler attribute)
(d3rlpy.preprocessing.StandardRewardScaler attribute)
T
TD3 (class in d3rlpy.algos)
TD3Config (class in d3rlpy.algos)
TD3PlusBC (class in d3rlpy.algos)
TD3PlusBCConfig (class in d3rlpy.algos)
TDErrorEvaluator (class in d3rlpy.metrics)
TensorboardAdapter (class in d3rlpy.logging)
TensorboardAdapterFactory (class in d3rlpy.logging)
to_dict() (d3rlpy.models.AdamFactory method)
(d3rlpy.models.DefaultEncoderFactory method)
(d3rlpy.models.GPTAdamWFactory method)
(d3rlpy.models.IQNQFunctionFactory method)
(d3rlpy.models.MeanQFunctionFactory method)
(d3rlpy.models.OptimizerFactory method)
(d3rlpy.models.PixelEncoderFactory method)
(d3rlpy.models.QRQFunctionFactory method)
(d3rlpy.models.RMSpropFactory method)
(d3rlpy.models.SGDFactory method)
(d3rlpy.models.VectorEncoderFactory method)
(d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxObservationScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MultiplyRewardScaler method)
(d3rlpy.preprocessing.PixelObservationScaler method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler method)
(d3rlpy.preprocessing.StandardObservationScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
to_json() (d3rlpy.models.AdamFactory method)
(d3rlpy.models.DefaultEncoderFactory method)
(d3rlpy.models.GPTAdamWFactory method)
(d3rlpy.models.IQNQFunctionFactory method)
(d3rlpy.models.MeanQFunctionFactory method)
(d3rlpy.models.OptimizerFactory method)
(d3rlpy.models.PixelEncoderFactory method)
(d3rlpy.models.QRQFunctionFactory method)
(d3rlpy.models.RMSpropFactory method)
(d3rlpy.models.SGDFactory method)
(d3rlpy.models.VectorEncoderFactory method)
(d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxObservationScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MultiplyRewardScaler method)
(d3rlpy.preprocessing.PixelObservationScaler method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler method)
(d3rlpy.preprocessing.StandardObservationScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
trajectory_slicer (d3rlpy.dataset.MDPDataset attribute)
(d3rlpy.dataset.ReplayBuffer attribute)
TrajectorySlicerProtocol (class in d3rlpy.dataset)
transform() (d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxObservationScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MultiplyRewardScaler method)
(d3rlpy.preprocessing.PixelObservationScaler method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler method)
(d3rlpy.preprocessing.StandardObservationScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
transform_numpy() (d3rlpy.preprocessing.ClipRewardScaler method)
(d3rlpy.preprocessing.ConstantShiftRewardScaler method)
(d3rlpy.preprocessing.MinMaxActionScaler method)
(d3rlpy.preprocessing.MinMaxObservationScaler method)
(d3rlpy.preprocessing.MinMaxRewardScaler method)
(d3rlpy.preprocessing.MultiplyRewardScaler method)
(d3rlpy.preprocessing.PixelObservationScaler method)
(d3rlpy.preprocessing.ReturnBasedRewardScaler method)
(d3rlpy.preprocessing.StandardObservationScaler method)
(d3rlpy.preprocessing.StandardRewardScaler method)
TransformerActionSampler (class in d3rlpy.algos)
TransformerAlgoBase (class in d3rlpy.algos)
transition_count (d3rlpy.dataset.BufferProtocol attribute)
(d3rlpy.dataset.FIFOBuffer attribute)
(d3rlpy.dataset.InfiniteBuffer attribute)
(d3rlpy.dataset.MDPDataset attribute)
(d3rlpy.dataset.ReplayBuffer attribute)
transition_picker (d3rlpy.dataset.MDPDataset attribute)
(d3rlpy.dataset.ReplayBuffer attribute)
TransitionPickerProtocol (class in d3rlpy.dataset)
U
update() (d3rlpy.algos.QLearningAlgoBase method)
(d3rlpy.algos.TransformerAlgoBase method)
(d3rlpy.ope.DiscreteFQE method)
(d3rlpy.ope.FQE method)
use_batch_norm (d3rlpy.models.DefaultEncoderFactory attribute)
(d3rlpy.models.PixelEncoderFactory attribute)
(d3rlpy.models.VectorEncoderFactory attribute)
V
VectorEncoderFactory (class in d3rlpy.models)
W
weight_decay (d3rlpy.models.AdamFactory attribute)
(d3rlpy.models.GPTAdamWFactory attribute)
(d3rlpy.models.RMSpropFactory attribute)
(d3rlpy.models.SGDFactory attribute)
write_metric() (d3rlpy.logging.CombineAdapter method)
(d3rlpy.logging.FileAdapter method)
(d3rlpy.logging.LoggerAdapter method)
(d3rlpy.logging.NoopAdapter method)
(d3rlpy.logging.TensorboardAdapter method)
write_params() (d3rlpy.logging.CombineAdapter method)
(d3rlpy.logging.FileAdapter method)
(d3rlpy.logging.LoggerAdapter method)
(d3rlpy.logging.NoopAdapter method)
(d3rlpy.logging.TensorboardAdapter method)
WriterPreprocessProtocol (class in d3rlpy.dataset)
Read the Docs
v: v2.2.0
Versions
latest
stable
v2.2.0
v2.1.0
v2.0.4
v2.0.3
v2.0.2
v1.1.1
v1.1.0
v1.0.0
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