RLax
latest
API Documentation
Value Learning
Policy Optimization
Exploration
Utilities
General Value Functions
Pop Art
Transforms
Losses
Distributions
RLax
»
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
_
__call__() (rlax.AllSum method)
__getnewargs__() (rlax.LagrangePenalty method)
(rlax.PopArtState method)
__init__() (rlax.AllSum method)
__new__() (rlax.PopArtState static method)
A
add_dirichlet_noise() (in module rlax)
add_gaussian_noise() (in module rlax)
add_ornstein_uhlenbeck_noise() (in module rlax)
AllSum (class in rlax)
alpha() (rlax.LagrangePenalty property)
art() (in module rlax)
B
batched_index() (in module rlax)
C
categorical_cross_entropy() (in module rlax)
categorical_double_q_learning() (in module rlax)
categorical_importance_sampling_ratios() (in module rlax)
categorical_kl_divergence() (in module rlax)
categorical_l2_project() (in module rlax)
categorical_q_learning() (in module rlax)
categorical_sample() (in module rlax)
categorical_td_learning() (in module rlax)
clip_gradient() (in module rlax)
clipped_entropy_softmax() (in module rlax)
clipped_surrogate_pg_loss() (in module rlax)
compute_parametric_kl_penalty_and_dual_loss() (in module rlax)
conditional_update() (in module rlax)
D
discounted_returns() (in module rlax)
double_q_learning() (in module rlax)
dpg_loss() (in module rlax)
E
embed_oar() (in module rlax)
entropy_loss() (in module rlax)
episodic_memory_intrinsic_rewards() (in module rlax)
epsilon() (rlax.LagrangePenalty property)
epsilon_greedy() (in module rlax)
epsilon_softmax() (in module rlax)
expected_sarsa() (in module rlax)
F
feature_control_rewards() (in module rlax)
G
gaussian_diagonal() (in module rlax)
general_off_policy_returns_from_action_values() (in module rlax)
general_off_policy_returns_from_q_and_v() (in module rlax)
greedy() (in module rlax)
H
huber_loss() (in module rlax)
I
identity() (in module rlax)
incremental_update() (in module rlax)
L
l2_loss() (in module rlax)
LagrangePenalty (class in rlax)
lambda_returns() (in module rlax)
leaky_vtrace() (in module rlax)
leaky_vtrace_td_error_and_advantage() (in module rlax)
lhs_broadcast() (in module rlax)
likelihood() (in module rlax)
log_loss() (in module rlax)
logit() (in module rlax)
M
mpo_compute_weights_and_temperature_loss() (in module rlax)
mpo_loss() (in module rlax)
multivariate_normal_kl_divergence() (in module rlax)
N
n_step_bootstrapped_returns() (in module rlax)
normalize() (in module rlax)
O
one_hot() (in module rlax)
P
per_dimension() (rlax.LagrangePenalty property)
periodic_update() (in module rlax)
persistent_q_learning() (in module rlax)
pixel_control_loss() (in module rlax)
pixel_control_rewards() (in module rlax)
policy_gradient_loss() (in module rlax)
pop() (in module rlax)
popart() (in module rlax)
PopArtState (class in rlax)
power() (in module rlax)
Q
q_lambda() (in module rlax)
q_learning() (in module rlax)
qpg_loss() (in module rlax)
quantile_expected_sarsa() (in module rlax)
quantile_q_learning() (in module rlax)
qv_learning() (in module rlax)
qv_max() (in module rlax)
R
retrace() (in module rlax)
retrace_continuous() (in module rlax)
rm_loss() (in module rlax)
rpg_loss() (in module rlax)
S
safe_epsilon_softmax() (in module rlax)
sarsa() (in module rlax)
sarsa_lambda() (in module rlax)
scale() (rlax.PopArtState property)
second_moment() (rlax.PopArtState property)
shift() (rlax.PopArtState property)
sigmoid() (in module rlax)
signed_expm1() (in module rlax)
signed_hyperbolic() (in module rlax)
signed_logp1() (in module rlax)
signed_parabolic() (in module rlax)
softmax() (in module rlax)
squashed_gaussian() (in module rlax)
T
td_lambda() (in module rlax)
td_learning() (in module rlax)
transform_from_2hot() (in module rlax)
transform_to_2hot() (in module rlax)
transformed_general_off_policy_returns_from_action_values() (in module rlax)
transformed_lambda_returns() (in module rlax)
transformed_n_step_q_learning() (in module rlax)
transformed_n_step_returns() (in module rlax)
transformed_q_lambda() (in module rlax)
transformed_retrace() (in module rlax)
tree_map_zipped() (in module rlax)
tree_select() (in module rlax)
tree_split_key() (in module rlax)
tree_split_leaves() (in module rlax)
truncated_generalized_advantage_estimation() (in module rlax)
U
unnormalize() (in module rlax)
unnormalize_linear() (in module rlax)
V
vmpo_compute_weights_and_temperature_loss() (in module rlax)
vmpo_loss() (in module rlax)
vtrace() (in module rlax)
Read the Docs
v: latest
Versions
latest
stable
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds