PFRL
stable
Installation
Quickstart Guide
API Reference
PFRL
Docs
»
Index
Edit on GitHub
Index
_
|
A
|
B
|
C
|
D
|
E
|
F
|
G
|
I
|
L
|
M
|
O
|
P
|
Q
|
R
|
S
|
T
_
__call__() (pfrl.q_function.StateActionQFunction method)
(pfrl.q_function.StateQFunction method)
A
A2C (class in pfrl.agents)
A3C (class in pfrl.agents)
ACER (class in pfrl.agents)
act() (pfrl.agent.Agent method)
ActionValue (class in pfrl.action_value)
AdditiveGaussian (class in pfrl.explorers)
AdditiveOU (class in pfrl.explorers)
Agent (class in pfrl.agent)
AL (class in pfrl.agents)
append() (pfrl.replay_buffers.ReplayBuffer method)
B
Boltzmann (class in pfrl.explorers)
Branched (class in pfrl.nn)
C
CategoricalDoubleDQN (class in pfrl.agents)
CategoricalDQN (class in pfrl.agents)
ConstantEpsilonGreedy (class in pfrl.explorers)
D
DDPG (class in pfrl.agents)
DeterministicHead (class in pfrl.policies)
DiscreteActionValue (class in pfrl.action_value)
DistributionalDuelingDQN (class in pfrl.q_functions)
DistributionalFCStateQFunctionWithDiscreteAction (class in pfrl.q_functions)
DistributionalSingleModelStateQFunctionWithDiscreteAction (class in pfrl.q_functions)
DoubleDQN (class in pfrl.agents)
DoublePAL (class in pfrl.agents)
DPP (class in pfrl.agents)
DQN (class in pfrl.agents)
DuelingDQN (class in pfrl.q_functions)
E
EmpiricalNormalization (class in pfrl.nn)
EpisodicReplayBuffer (class in pfrl.replay_buffers)
evaluate_actions() (pfrl.action_value.ActionValue method)
Explorer (class in pfrl.explorer)
F
FactorizedNoisyLinear (class in pfrl.nn)
FCBNLateActionSAQFunction (class in pfrl.q_functions)
FCBNSAQFunction (class in pfrl.q_functions)
FCLateActionSAQFunction (class in pfrl.q_functions)
FCLSTMSAQFunction (class in pfrl.q_functions)
FCQuadraticStateQFunction (class in pfrl.q_functions)
FCSAQFunction (class in pfrl.q_functions)
FCStateQFunctionWithDiscreteAction (class in pfrl.q_functions)
forward() (pfrl.nn.Recurrent method)
G
GaussianHeadWithDiagonalCovariance (class in pfrl.policies)
GaussianHeadWithFixedCovariance (class in pfrl.policies)
GaussianHeadWithStateIndependentCovariance (class in pfrl.policies)
generate_exp_id() (in module pfrl.experiments)
get_statistics() (pfrl.agent.Agent method)
Greedy (class in pfrl.explorers)
greedy_actions (pfrl.action_value.ActionValue attribute)
I
IQN (class in pfrl.agents)
L
LargeAtariCNN (class in pfrl.nn)
LinearDecayEpsilonGreedy (class in pfrl.explorers)
LinearInterpolationHook (class in pfrl.experiments)
load() (pfrl.agent.Agent method)
(pfrl.replay_buffers.ReplayBuffer method)
M
max (pfrl.action_value.ActionValue attribute)
MLP (class in pfrl.nn)
MLPBN (class in pfrl.nn)
O
observe() (pfrl.agent.Agent method)
P
PAL (class in pfrl.agents)
params (pfrl.action_value.ActionValue attribute)
PersistentEpisodicReplayBuffer (class in pfrl.replay_buffers)
PersistentReplayBuffer (class in pfrl.replay_buffers)
PPO (class in pfrl.agents)
prepare_output_dir() (in module pfrl.experiments)
PrioritizedEpisodicReplayBuffer (class in pfrl.replay_buffers)
PrioritizedReplayBuffer (class in pfrl.replay_buffers)
Q
QuadraticActionValue (class in pfrl.action_value)
R
Recurrent (class in pfrl.nn)
RecurrentBranched (class in pfrl.nn)
RecurrentSequential (class in pfrl.nn)
REINFORCE (class in pfrl.agents)
ReplayBuffer (class in pfrl.replay_buffers)
,
[1]
S
sample() (pfrl.replay_buffers.ReplayBuffer method)
save() (pfrl.agent.Agent method)
(pfrl.replay_buffers.ReplayBuffer method)
select_action() (pfrl.explorer.Explorer method)
SingleActionValue (class in pfrl.action_value)
SingleModelStateActionQFunction (class in pfrl.q_functions)
SingleModelStateQFunctionWithDiscreteAction (class in pfrl.q_functions)
SmallAtariCNN (class in pfrl.nn)
SoftActorCritic (class in pfrl.agents)
SoftmaxCategoricalHead (class in pfrl.policies)
StateActionQFunction (class in pfrl.q_function)
StateQFunction (class in pfrl.q_function)
StepHook (class in pfrl.experiments)
stop_current_episode() (pfrl.replay_buffers.ReplayBuffer method)
T
TD3 (class in pfrl.agents)
to_factorized_noisy() (in module pfrl.nn)
train_agent_async() (in module pfrl.experiments)
train_agent_batch() (in module pfrl.experiments)
train_agent_batch_with_evaluation() (in module pfrl.experiments)
train_agent_with_evaluation() (in module pfrl.experiments)
TRPO (class in pfrl.agents)
Read the Docs
v: stable
Versions
latest
stable
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds
Free document hosting provided by
Read the Docs
.