meta_policy_search
latest
Contents:
Meta-Policy Search
meta_policy_search
Docs
»
Index
Edit on GitHub
Index
B
|
C
|
D
|
E
|
F
|
G
|
K
|
L
|
M
|
N
|
O
|
P
|
R
|
S
|
T
|
U
|
V
B
Baseline (class in meta_policy_search.baselines)
build_graph() (meta_policy_search.meta_algos.MAMLAlgo method)
(meta_policy_search.meta_algos.ProMP method)
(meta_policy_search.meta_algos.TRPOMAML method)
(meta_policy_search.meta_algos.VPGMAML method)
(meta_policy_search.optimizers.ConjugateGradientOptimizer method)
(meta_policy_search.optimizers.MAMLFirstOrderOptimizer method)
(meta_policy_search.policies.GaussianMLPPolicy method)
(meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
(meta_policy_search.policies.Policy method)
C
ConjugateGradientOptimizer (class in meta_policy_search.optimizers)
constraint_val() (meta_policy_search.optimizers.ConjugateGradientOptimizer method)
D
DiagonalGaussian (class in meta_policy_search.policies.distributions.diagonal_gaussian)
DiceSampleProcessor (class in meta_policy_search.samplers)
dim (meta_policy_search.policies.distributions.base.Distribution attribute)
(meta_policy_search.policies.distributions.diagonal_gaussian.DiagonalGaussian attribute)
dist_info_keys (meta_policy_search.policies.distributions.base.Distribution attribute)
dist_info_specs (meta_policy_search.policies.distributions.base.Distribution attribute)
(meta_policy_search.policies.distributions.diagonal_gaussian.DiagonalGaussian attribute)
Distribution (class in meta_policy_search.policies.distributions.base)
distribution (meta_policy_search.policies.GaussianMLPPolicy attribute)
(meta_policy_search.policies.MetaGaussianMLPPolicy attribute)
(meta_policy_search.policies.MetaPolicy attribute)
(meta_policy_search.policies.Policy attribute)
distribution_info_keys() (meta_policy_search.policies.GaussianMLPPolicy method)
(meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
(meta_policy_search.policies.Policy method)
distribution_info_sym() (meta_policy_search.policies.GaussianMLPPolicy method)
(meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
(meta_policy_search.policies.Policy method)
E
entropy() (meta_policy_search.policies.distributions.base.Distribution method)
(meta_policy_search.policies.distributions.diagonal_gaussian.DiagonalGaussian method)
entropy_sym() (meta_policy_search.policies.distributions.base.Distribution method)
(meta_policy_search.policies.distributions.diagonal_gaussian.DiagonalGaussian method)
F
fit() (meta_policy_search.baselines.Baseline method)
(meta_policy_search.baselines.LinearFeatureBaseline method)
(meta_policy_search.baselines.LinearTimeBaseline method)
G
GaussianMLPPolicy (class in meta_policy_search.policies)
get_action() (meta_policy_search.policies.GaussianMLPPolicy method)
(meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
(meta_policy_search.policies.Policy method)
get_actions() (meta_policy_search.policies.GaussianMLPPolicy method)
(meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
(meta_policy_search.policies.Policy method)
get_itr_snapshot() (meta_policy_search.meta_trainer.Trainer method)
get_param_values() (meta_policy_search.baselines.Baseline method)
(meta_policy_search.baselines.LinearFeatureBaseline method)
(meta_policy_search.baselines.LinearTimeBaseline method)
(meta_policy_search.policies.GaussianMLPPolicy method)
(meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
(meta_policy_search.policies.Policy method)
get_params() (meta_policy_search.policies.GaussianMLPPolicy method)
(meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
(meta_policy_search.policies.Policy method)
get_task() (meta_policy_search.envs.base.MetaEnv method)
gradient() (meta_policy_search.optimizers.ConjugateGradientOptimizer method)
K
kl() (meta_policy_search.policies.distributions.base.Distribution method)
(meta_policy_search.policies.distributions.diagonal_gaussian.DiagonalGaussian method)
kl_sym() (meta_policy_search.policies.distributions.base.Distribution method)
(meta_policy_search.policies.distributions.diagonal_gaussian.DiagonalGaussian method)
L
likelihood_ratio() (meta_policy_search.policies.distributions.base.Distribution method)
likelihood_ratio_sym() (meta_policy_search.policies.distributions.base.Distribution method)
(meta_policy_search.policies.GaussianMLPPolicy method)
(meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
(meta_policy_search.policies.Policy method)
(meta_policy_search.policies.distributions.diagonal_gaussian.DiagonalGaussian method)
LinearFeatureBaseline (class in meta_policy_search.baselines)
LinearTimeBaseline (class in meta_policy_search.baselines)
load_params() (meta_policy_search.policies.GaussianMLPPolicy method)
(meta_policy_search.policies.MetaGaussianMLPPolicy method)
log_diagnostics() (meta_policy_search.baselines.Baseline method)
(meta_policy_search.baselines.LinearFeatureBaseline method)
(meta_policy_search.baselines.LinearTimeBaseline method)
(meta_policy_search.envs.base.MetaEnv method)
(meta_policy_search.policies.GaussianMLPPolicy method)
(meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
(meta_policy_search.policies.Policy method)
log_likelihood() (meta_policy_search.policies.distributions.base.Distribution method)
(meta_policy_search.policies.distributions.diagonal_gaussian.DiagonalGaussian method)
log_likelihood_sym() (meta_policy_search.policies.distributions.base.Distribution method)
(meta_policy_search.policies.GaussianMLPPolicy method)
(meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
(meta_policy_search.policies.Policy method)
(meta_policy_search.policies.distributions.diagonal_gaussian.DiagonalGaussian method)
loss() (meta_policy_search.optimizers.ConjugateGradientOptimizer method)
(meta_policy_search.optimizers.MAMLFirstOrderOptimizer method)
M
make_vars() (meta_policy_search.meta_algos.MAMLAlgo method)
(meta_policy_search.meta_algos.ProMP method)
(meta_policy_search.meta_algos.TRPOMAML method)
(meta_policy_search.meta_algos.VPGMAML method)
MAMLAlgo (class in meta_policy_search.meta_algos)
MAMLFirstOrderOptimizer (class in meta_policy_search.optimizers)
meta_policy_search.baselines (module)
meta_policy_search.envs.base (module)
meta_policy_search.meta_algos (module)
meta_policy_search.meta_trainer (module)
meta_policy_search.optimizers (module)
meta_policy_search.policies (module)
meta_policy_search.policies.distributions (module)
meta_policy_search.policies.distributions.base (module)
meta_policy_search.policies.distributions.diagonal_gaussian (module)
meta_policy_search.samplers (module)
meta_policy_search.samplers.vectorized_env_executor (module)
MetaEnv (class in meta_policy_search.envs.base)
MetaGaussianMLPPolicy (class in meta_policy_search.policies)
MetaIterativeEnvExecutor (class in meta_policy_search.samplers.vectorized_env_executor)
MetaParallelEnvExecutor (class in meta_policy_search.samplers.vectorized_env_executor)
MetaPolicy (class in meta_policy_search.policies)
MetaSampleProcessor (class in meta_policy_search.samplers)
MetaSampler (class in meta_policy_search.samplers)
N
num_envs (meta_policy_search.samplers.vectorized_env_executor.MetaIterativeEnvExecutor attribute)
(meta_policy_search.samplers.vectorized_env_executor.MetaParallelEnvExecutor attribute)
O
obtain_samples() (meta_policy_search.samplers.MetaSampler method)
(meta_policy_search.samplers.Sampler method)
optimize() (meta_policy_search.optimizers.ConjugateGradientOptimizer method)
(meta_policy_search.optimizers.MAMLFirstOrderOptimizer method)
optimize_policy() (meta_policy_search.meta_algos.MAMLAlgo method)
(meta_policy_search.meta_algos.ProMP method)
(meta_policy_search.meta_algos.TRPOMAML method)
(meta_policy_search.meta_algos.VPGMAML method)
P
policies_params_feed_dict (meta_policy_search.policies.MetaGaussianMLPPolicy attribute)
(meta_policy_search.policies.MetaPolicy attribute)
Policy (class in meta_policy_search.policies)
predict() (meta_policy_search.baselines.Baseline method)
(meta_policy_search.baselines.LinearFeatureBaseline method)
(meta_policy_search.baselines.LinearTimeBaseline method)
process_samples() (meta_policy_search.samplers.DiceSampleProcessor method)
(meta_policy_search.samplers.MetaSampleProcessor method)
(meta_policy_search.samplers.SampleProcessor method)
ProMP (class in meta_policy_search.meta_algos)
R
reset() (meta_policy_search.samplers.vectorized_env_executor.MetaIterativeEnvExecutor method)
(meta_policy_search.samplers.vectorized_env_executor.MetaParallelEnvExecutor method)
S
sample() (meta_policy_search.policies.distributions.base.Distribution method)
(meta_policy_search.policies.distributions.diagonal_gaussian.DiagonalGaussian method)
sample_tasks() (meta_policy_search.envs.base.MetaEnv method)
SampleProcessor (class in meta_policy_search.samplers)
Sampler (class in meta_policy_search.samplers)
set_params() (meta_policy_search.baselines.Baseline method)
(meta_policy_search.baselines.LinearFeatureBaseline method)
(meta_policy_search.baselines.LinearTimeBaseline method)
(meta_policy_search.policies.GaussianMLPPolicy method)
(meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
(meta_policy_search.policies.Policy method)
set_task() (meta_policy_search.envs.base.MetaEnv method)
set_tasks() (meta_policy_search.samplers.vectorized_env_executor.MetaIterativeEnvExecutor method)
(meta_policy_search.samplers.vectorized_env_executor.MetaParallelEnvExecutor method)
step() (meta_policy_search.samplers.vectorized_env_executor.MetaIterativeEnvExecutor method)
(meta_policy_search.samplers.vectorized_env_executor.MetaParallelEnvExecutor method)
switch_to_pre_update() (meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
T
train() (meta_policy_search.meta_trainer.Trainer method)
Trainer (class in meta_policy_search.meta_trainer)
TRPOMAML (class in meta_policy_search.meta_algos)
U
update_task_parameters() (meta_policy_search.policies.MetaGaussianMLPPolicy method)
(meta_policy_search.policies.MetaPolicy method)
update_tasks() (meta_policy_search.samplers.MetaSampler method)
V
VPGMAML (class in meta_policy_search.meta_algos)
Read the Docs
v: latest
Versions
latest
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds
Free document hosting provided by
Read the Docs
.