keras-gym
stable
Example Notebooks
Function Approximators
Policies
Probability Distributions
Caching
Planning
Wrappers
Environments
Loss Functions
Utilities
Glossary
Release Notes
keras-gym
Docs
»
Index
Edit on GitHub
Index
_
|
A
|
B
|
C
|
D
|
E
|
F
|
G
|
H
|
I
|
K
|
L
|
M
|
N
|
O
|
P
|
Q
|
R
|
S
|
T
|
U
|
V
|
Z
_
__call__() (keras_gym.ActorCritic method)
(keras_gym.GaussianPolicy method)
(keras_gym.QTypeI method)
(keras_gym.QTypeII method)
(keras_gym.SoftActorCritic method)
(keras_gym.SoftmaxPolicy method)
(keras_gym.V method)
(keras_gym.losses.LoglossSign method)
(keras_gym.losses.ProjectedSemiGradientLoss method)
(keras_gym.losses.RootMeanSquaredError method)
(keras_gym.policies.EpsilonGreedy method)
(keras_gym.policies.RandomPolicy method)
(keras_gym.policies.UserInputPolicy method)
A
A
A_next
actor-critic
ActorCritic (class in keras_gym)
add() (keras_gym.caching.ExperienceReplayBuffer method)
(keras_gym.caching.MonteCarloCache method)
(keras_gym.caching.NStepCache method)
Adv
argmax() (in module keras_gym.utils)
argmin() (in module keras_gym.utils)
AtariFunctionApproximator (class in keras_gym.predefined)
B
backup() (keras_gym.planning.MCTSNode method)
batch_eval() (keras_gym.ActorCritic method)
(keras_gym.GaussianPolicy method)
(keras_gym.QTypeI method)
(keras_gym.QTypeII method)
(keras_gym.SoftActorCritic method)
(keras_gym.SoftmaxPolicy method)
(keras_gym.V method)
batch_update() (keras_gym.ActorCritic method)
(keras_gym.GaussianPolicy method)
(keras_gym.QTypeI method)
(keras_gym.QTypeII method)
(keras_gym.SoftActorCritic method)
(keras_gym.SoftmaxPolicy method)
(keras_gym.V method)
body
body() (keras_gym.FunctionApproximator method)
(keras_gym.predefined.AtariFunctionApproximator method)
(keras_gym.predefined.ConnectFourFunctionApproximator method)
(keras_gym.predefined.LinearFunctionApproximator method)
body_q1() (keras_gym.FunctionApproximator method)
(keras_gym.predefined.AtariFunctionApproximator method)
(keras_gym.predefined.ConnectFourFunctionApproximator method)
(keras_gym.predefined.LinearFunctionApproximator method)
bootstrap_target() (keras_gym.QTypeI method)
(keras_gym.QTypeII method)
box_to_reals_np() (in module keras_gym.utils)
box_to_reals_tf() (in module keras_gym.utils)
box_to_unit_interval_np() (in module keras_gym.utils)
box_to_unit_interval_tf() (in module keras_gym.utils)
BoxActionsToReals (class in keras_gym.wrappers)
C
call() (keras_gym.losses.LoglossSign method)
(keras_gym.losses.ProjectedSemiGradientLoss method)
(keras_gym.losses.RootMeanSquaredError method)
CategoricalDist (class in keras_gym.proba_dists)
check_numpy_array() (in module keras_gym.utils)
check_tensor() (in module keras_gym.utils)
clear() (keras_gym.caching.ExperienceReplayBuffer method)
clipped_logit_np() (in module keras_gym.utils)
close() (keras_gym.envs.ConnectFourEnv method)
(keras_gym.wrappers.BoxActionsToReals method)
(keras_gym.wrappers.FrameStacker method)
(keras_gym.wrappers.ImagePreprocessor method)
(keras_gym.wrappers.TrainMonitor method)
ConnectFourEnv (class in keras_gym.envs)
ConnectFourFunctionApproximator (class in keras_gym.predefined)
cross_entropy() (keras_gym.proba_dists.CategoricalDist method)
(keras_gym.proba_dists.NormalDist method)
D
DEFAULT_OPTIMIZER (keras_gym.FunctionApproximator attribute)
(keras_gym.predefined.AtariFunctionApproximator attribute)
(keras_gym.predefined.ConnectFourFunctionApproximator attribute)
(keras_gym.predefined.LinearFunctionApproximator attribute)
diff_transform_matrix() (in module keras_gym.utils)
dist_params() (keras_gym.ActorCritic method)
(keras_gym.GaussianPolicy method)
(keras_gym.SoftActorCritic method)
(keras_gym.SoftmaxPolicy method)
(keras_gym.policies.EpsilonGreedy method)
(keras_gym.policies.RandomPolicy method)
E
enable_logging() (in module keras_gym.utils)
entropy() (keras_gym.proba_dists.CategoricalDist method)
(keras_gym.proba_dists.NormalDist method)
EpsilonGreedy (class in keras_gym.policies)
expand() (keras_gym.planning.MCTSNode method)
ExperienceReplayBuffer (class in keras_gym.caching)
F
feature_vector() (in module keras_gym.utils)
flush() (keras_gym.caching.MonteCarloCache method)
(keras_gym.caching.NStepCache method)
forward_pass
FrameStacker (class in keras_gym.wrappers)
from_func() (keras_gym.ActorCritic class method)
(keras_gym.SoftActorCritic class method)
from_value_function() (keras_gym.caching.ExperienceReplayBuffer class method)
function approximator
FunctionApproximator (class in keras_gym)
G
G
GaussianPolicy (class in keras_gym)
generate_gif() (in module keras_gym.utils)
get_env_attr() (in module keras_gym.utils)
get_transition() (in module keras_gym.utils)
greedy() (keras_gym.ActorCritic method)
(keras_gym.GaussianPolicy method)
(keras_gym.SoftActorCritic method)
(keras_gym.SoftmaxPolicy method)
(keras_gym.policies.EpsilonGreedy method)
(keras_gym.policies.RandomPolicy method)
(keras_gym.policies.UserInputPolicy method)
H
has_env_attr() (in module keras_gym.utils)
head
head_pi() (keras_gym.FunctionApproximator method)
(keras_gym.predefined.AtariFunctionApproximator method)
(keras_gym.predefined.ConnectFourFunctionApproximator method)
(keras_gym.predefined.LinearFunctionApproximator method)
head_q1() (keras_gym.FunctionApproximator method)
(keras_gym.predefined.AtariFunctionApproximator method)
(keras_gym.predefined.ConnectFourFunctionApproximator method)
(keras_gym.predefined.LinearFunctionApproximator method)
head_q2() (keras_gym.FunctionApproximator method)
(keras_gym.predefined.AtariFunctionApproximator method)
(keras_gym.predefined.ConnectFourFunctionApproximator method)
(keras_gym.predefined.LinearFunctionApproximator method)
head_v() (keras_gym.FunctionApproximator method)
(keras_gym.predefined.AtariFunctionApproximator method)
(keras_gym.predefined.ConnectFourFunctionApproximator method)
(keras_gym.predefined.LinearFunctionApproximator method)
I
idx() (in module keras_gym.utils)
ImagePreprocessor (class in keras_gym.wrappers)
In
is_policy() (in module keras_gym.utils)
is_qfunction() (in module keras_gym.utils)
is_vfunction() (in module keras_gym.utils)
K
kl_divergence() (keras_gym.proba_dists.CategoricalDist method)
(keras_gym.proba_dists.NormalDist method)
L
LinearFunctionApproximator (class in keras_gym.predefined)
log_proba() (keras_gym.proba_dists.CategoricalDist method)
(keras_gym.proba_dists.NormalDist method)
log_softmax() (in module keras_gym.utils)
log_softmax_tf() (in module keras_gym.utils)
LoglossSign (class in keras_gym.losses)
M
MCTSNode (class in keras_gym.planning)
MonteCarloCache (class in keras_gym.caching)
N
NormalDist (class in keras_gym.proba_dists)
NStepCache (class in keras_gym.caching)
O
one_hot() (in module keras_gym.utils)
P
P
P_next
play() (keras_gym.planning.MCTSNode method)
policy_loss_with_metrics() (keras_gym.core.base.BaseUpdateablePolicy method)
(keras_gym.GaussianPolicy method)
(keras_gym.SoftmaxPolicy method)
pop() (keras_gym.caching.MonteCarloCache method)
(keras_gym.caching.NStepCache method)
predict_model
project_onto_actions_np() (in module keras_gym.utils)
project_onto_actions_tf() (in module keras_gym.utils)
,
[1]
ProjectedSemiGradientLoss (class in keras_gym.losses)
Q
Q_s
Q_sa
QTypeI (class in keras_gym)
QTypeII (class in keras_gym)
R
RandomPolicy (class in keras_gym.policies)
reals_to_box_np() (in module keras_gym.utils)
record_losses() (keras_gym.wrappers.TrainMonitor method)
render() (keras_gym.envs.ConnectFourEnv method)
(keras_gym.wrappers.BoxActionsToReals method)
(keras_gym.wrappers.FrameStacker method)
(keras_gym.wrappers.ImagePreprocessor method)
(keras_gym.wrappers.TrainMonitor method)
render_episode() (in module keras_gym.utils)
reset() (keras_gym.caching.MonteCarloCache method)
(keras_gym.caching.NStepCache method)
(keras_gym.envs.ConnectFourEnv method)
(keras_gym.wrappers.BoxActionsToReals method)
(keras_gym.wrappers.FrameStacker method)
(keras_gym.wrappers.ImagePreprocessor method)
(keras_gym.wrappers.TrainMonitor method)
reset_global() (keras_gym.wrappers.TrainMonitor method)
Rn
RootMeanSquaredError (class in keras_gym.losses)
S
S
S_next
sample() (keras_gym.caching.ExperienceReplayBuffer method)
(keras_gym.proba_dists.CategoricalDist method)
(keras_gym.proba_dists.NormalDist method)
search() (keras_gym.planning.MCTSNode method)
seed() (keras_gym.envs.ConnectFourEnv method)
(keras_gym.wrappers.BoxActionsToReals method)
(keras_gym.wrappers.FrameStacker method)
(keras_gym.wrappers.ImagePreprocessor method)
(keras_gym.wrappers.TrainMonitor method)
select() (keras_gym.planning.MCTSNode method)
set_epsilon() (keras_gym.policies.EpsilonGreedy method)
set_tf_loglevel() (in module keras_gym.utils)
show() (keras_gym.planning.MCTSNode method)
SoftActorCritic (class in keras_gym)
softmax() (in module keras_gym.utils)
SoftmaxPolicy (class in keras_gym)
state value function
step() (keras_gym.envs.ConnectFourEnv method)
(keras_gym.wrappers.BoxActionsToReals method)
(keras_gym.wrappers.FrameStacker method)
(keras_gym.wrappers.ImagePreprocessor method)
(keras_gym.wrappers.TrainMonitor method)
sync_target_model() (keras_gym.ActorCritic method)
(keras_gym.GaussianPolicy method)
(keras_gym.QTypeI method)
(keras_gym.QTypeII method)
(keras_gym.SoftActorCritic method)
(keras_gym.SoftmaxPolicy method)
(keras_gym.V method)
T
target_model
train_model
TrainMonitor (class in keras_gym.wrappers)
type-I state-action value function
type-II state-action value function
U
unit_interval_to_box_np() (in module keras_gym.utils)
unit_interval_to_box_tf() (in module keras_gym.utils)
unwrapped (keras_gym.envs.ConnectFourEnv attribute)
(keras_gym.wrappers.BoxActionsToReals attribute)
(keras_gym.wrappers.FrameStacker attribute)
(keras_gym.wrappers.ImagePreprocessor attribute)
(keras_gym.wrappers.TrainMonitor attribute)
update() (keras_gym.ActorCritic method)
(keras_gym.GaussianPolicy method)
(keras_gym.QTypeI method)
(keras_gym.QTypeII method)
(keras_gym.SoftActorCritic method)
(keras_gym.SoftmaxPolicy method)
(keras_gym.V method)
updateable policy
UserInputPolicy (class in keras_gym.policies)
V
V
(class in keras_gym)
Z
Z
Read the Docs
v: stable
Versions
latest
stable
Downloads
html
On Read the Docs
Project Home
Builds
Free document hosting provided by
Read the Docs
.