actor-critic
latest
API Documentation
Quickstart Guide
actor-critic
Docs
»
Index
Edit on GitHub
Index
_
|
A
|
B
|
C
|
D
|
E
|
F
|
G
|
I
|
L
|
M
|
O
|
P
|
R
|
S
|
T
|
V
_
__init__() (actorcritic.agents.MultiEnvAgent method)
(actorcritic.agents.SingleEnvAgent method)
(actorcritic.baselines.StateValueFunction method)
(actorcritic.envs.atari.model.AtariModel method)
(actorcritic.envs.atari.wrappers.AtariClipRewardWrapper method)
(actorcritic.envs.atari.wrappers.AtariEpisodicLifeWrapper method)
(actorcritic.envs.atari.wrappers.AtariFireResetWrapper method)
(actorcritic.envs.atari.wrappers.AtariFrameskipWrapper method)
(actorcritic.envs.atari.wrappers.AtariInfoClearWrapper method)
(actorcritic.envs.atari.wrappers.AtariNoopResetWrapper method)
(actorcritic.envs.atari.wrappers.AtariPreprocessFrameWrapper method)
(actorcritic.envs.atari.wrappers.EpisodeInfoWrapper method)
(actorcritic.envs.atari.wrappers.FrameStackWrapper method)
(actorcritic.envs.atari.wrappers.RenderWrapper method)
(actorcritic.kfac_utils.ColdStartPeriodicInvUpdateKfacOpt method)
(actorcritic.model.ActorCriticModel method)
(actorcritic.multi_env.MultiEnv method)
(actorcritic.multi_env.SubprocessEnv method)
(actorcritic.nn.ClipGlobalNormOptimizer method)
(actorcritic.objectives.A2CObjective method)
(actorcritic.policies.DistributionPolicy method)
(actorcritic.policies.SoftmaxPolicy method)
_AutoResetWrapper (class in actorcritic.multi_env)
A
A2CObjective (class in actorcritic.objectives)
action_space (actorcritic.multi_env.MultiEnv attribute)
(actorcritic.multi_env.SubprocessEnv attribute)
actions_placeholder (actorcritic.model.ActorCriticModel attribute)
actorcritic (module)
actorcritic.agents (module)
actorcritic.baselines (module)
actorcritic.envs (module)
actorcritic.envs.atari (module)
actorcritic.envs.atari.model (module)
actorcritic.envs.atari.wrappers (module)
actorcritic.examples (module)
actorcritic.examples.atari (module)
actorcritic.examples.atari.a2c_acktr (module)
actorcritic.kfac_utils (module)
actorcritic.model (module)
actorcritic.multi_env (module)
actorcritic.nn (module)
actorcritic.objectives (module)
actorcritic.policies (module)
ActorCriticModel (class in actorcritic.model)
ActorCriticObjective (class in actorcritic.objectives)
Agent (class in actorcritic.agents)
apply_gradients() (actorcritic.kfac_utils.ColdStartPeriodicInvUpdateKfacOpt method)
(actorcritic.nn.ClipGlobalNormOptimizer method)
AtariClipRewardWrapper (class in actorcritic.envs.atari.wrappers)
AtariEpisodicLifeWrapper (class in actorcritic.envs.atari.wrappers)
AtariFireResetWrapper (class in actorcritic.envs.atari.wrappers)
AtariFrameskipWrapper (class in actorcritic.envs.atari.wrappers)
AtariInfoClearWrapper (class in actorcritic.envs.atari.wrappers)
AtariModel (class in actorcritic.envs.atari.model)
AtariNoopResetWrapper (class in actorcritic.envs.atari.wrappers)
AtariPreprocessFrameWrapper (class in actorcritic.envs.atari.wrappers)
B
baseline (actorcritic.model.ActorCriticModel attribute)
Baseline (class in actorcritic.baselines)
baseline_loss (actorcritic.objectives.A2CObjective attribute)
(actorcritic.objectives.ActorCriticObjective attribute)
bootstrap_observations_placeholder (actorcritic.model.ActorCriticModel attribute)
bootstrap_values (actorcritic.model.ActorCriticModel attribute)
C
ClipGlobalNormOptimizer (class in actorcritic.nn)
close() (actorcritic.multi_env.MultiEnv method)
(actorcritic.multi_env.SubprocessEnv method)
ColdStartPeriodicInvUpdateKfacOpt (class in actorcritic.kfac_utils)
conv2d() (in module actorcritic.nn)
conv2d_params() (in module actorcritic.nn)
create_environments() (in module actorcritic.examples.atari.a2c_acktr)
create_optimizer() (in module actorcritic.examples.atari.a2c_acktr)
create_subprocess_envs() (in module actorcritic.multi_env)
D
DistributionPolicy (class in actorcritic.policies)
E
entropy (actorcritic.policies.DistributionPolicy attribute)
(actorcritic.policies.Policy attribute)
envs (actorcritic.multi_env.MultiEnv attribute)
EpisodeInfoWrapper (class in actorcritic.envs.atari.wrappers)
F
flatten() (in module actorcritic.nn)
FrameStackWrapper (class in actorcritic.envs.atari.wrappers)
fully_connected() (in module actorcritic.nn)
fully_connected_params() (in module actorcritic.nn)
G
get_episode_rewards_from_info_batch() (actorcritic.envs.atari.wrappers.EpisodeInfoWrapper static method)
I
initialize() (actorcritic.multi_env.SubprocessEnv method)
interact() (actorcritic.agents.Agent method)
(actorcritic.agents.MultiEnvAgent method)
(actorcritic.agents.SingleEnvAgent method)
L
linear_decay() (in module actorcritic.nn)
load_model() (in module actorcritic.examples.atari.a2c_acktr)
log_prob (actorcritic.policies.DistributionPolicy attribute)
(actorcritic.policies.Policy attribute)
M
make_atari_env() (in module actorcritic.examples.atari.a2c_acktr)
mean_entropy (actorcritic.objectives.A2CObjective attribute)
mode (actorcritic.policies.DistributionPolicy attribute)
(actorcritic.policies.Policy attribute)
MultiEnv (class in actorcritic.multi_env)
MultiEnvAgent (class in actorcritic.agents)
O
observation_space (actorcritic.multi_env.MultiEnv attribute)
(actorcritic.multi_env.SubprocessEnv attribute)
observations_placeholder (actorcritic.model.ActorCriticModel attribute)
optimize_separate() (actorcritic.objectives.ActorCriticObjective method)
optimize_shared() (actorcritic.objectives.ActorCriticObjective method)
P
policy (actorcritic.model.ActorCriticModel attribute)
Policy (class in actorcritic.policies)
policy_loss (actorcritic.objectives.A2CObjective attribute)
(actorcritic.objectives.ActorCriticObjective attribute)
R
register_layers() (actorcritic.envs.atari.model.AtariModel method)
(actorcritic.model.ActorCriticModel method)
register_predictive_distribution() (actorcritic.baselines.Baseline method)
(actorcritic.baselines.StateValueFunction method)
(actorcritic.policies.Policy method)
(actorcritic.policies.SoftmaxPolicy method)
register_predictive_distributions() (actorcritic.model.ActorCriticModel method)
render() (actorcritic.multi_env.SubprocessEnv method)
RenderWrapper (class in actorcritic.envs.atari.wrappers)
reset() (actorcritic.envs.atari.wrappers.AtariEpisodicLifeWrapper method)
(actorcritic.envs.atari.wrappers.AtariFireResetWrapper method)
(actorcritic.envs.atari.wrappers.AtariFrameskipWrapper method)
(actorcritic.envs.atari.wrappers.AtariInfoClearWrapper method)
(actorcritic.envs.atari.wrappers.AtariNoopResetWrapper method)
(actorcritic.envs.atari.wrappers.EpisodeInfoWrapper method)
(actorcritic.envs.atari.wrappers.FrameStackWrapper method)
(actorcritic.envs.atari.wrappers.RenderWrapper method)
(actorcritic.multi_env.MultiEnv method)
(actorcritic.multi_env.SubprocessEnv method)
(actorcritic.multi_env._AutoResetWrapper method)
rewards_placeholder (actorcritic.model.ActorCriticModel attribute)
S
sample (actorcritic.policies.DistributionPolicy attribute)
(actorcritic.policies.Policy attribute)
sample_actions() (actorcritic.model.ActorCriticModel method)
save_model() (in module actorcritic.examples.atari.a2c_acktr)
select_max_actions() (actorcritic.model.ActorCriticModel method)
SingleEnvAgent (class in actorcritic.agents)
SoftmaxPolicy (class in actorcritic.policies)
start() (actorcritic.multi_env.SubprocessEnv method)
StateValueFunction (class in actorcritic.baselines)
step() (actorcritic.envs.atari.wrappers.AtariEpisodicLifeWrapper method)
(actorcritic.envs.atari.wrappers.AtariFireResetWrapper method)
(actorcritic.envs.atari.wrappers.AtariFrameskipWrapper method)
(actorcritic.envs.atari.wrappers.AtariInfoClearWrapper method)
(actorcritic.envs.atari.wrappers.AtariNoopResetWrapper method)
(actorcritic.envs.atari.wrappers.EpisodeInfoWrapper method)
(actorcritic.envs.atari.wrappers.FrameStackWrapper method)
(actorcritic.envs.atari.wrappers.RenderWrapper method)
(actorcritic.multi_env.MultiEnv method)
(actorcritic.multi_env.SubprocessEnv method)
(actorcritic.multi_env._AutoResetWrapper method)
SubprocessEnv (class in actorcritic.multi_env)
T
terminals_placeholder (actorcritic.model.ActorCriticModel attribute)
train_a2c_acktr() (in module actorcritic.examples.atari.a2c_acktr)
transpose_list() (in module actorcritic.agents)
V
value (actorcritic.baselines.Baseline attribute)
(actorcritic.baselines.StateValueFunction attribute)
Read the Docs
v: latest
Versions
latest
Downloads
pdf
htmlzip
epub
On Read the Docs
Project Home
Builds
Free document hosting provided by
Read the Docs
.