rlpyt
latest
Contents:
Base Classes and Interfaces
Policy Gradient Implementations
Deep Q-Learning Implementations
Q-Value Policy Gradient Implementations
Runners
Samplers
Asynchronous Samplers
Collectors
Distributions
Spaces
Model Components
Environments
Replay Buffers
Named Array Tuples
Utilities
Logger
Creating and Launching Experiments
rlpyt
Docs
»
Index
Edit on GitHub
Index
_
|
A
|
B
|
C
|
D
|
E
|
F
|
G
|
I
|
K
|
L
|
M
|
N
|
O
|
P
|
Q
|
R
|
S
|
T
|
U
|
V
|
Z
_
__call__() (rlpyt.agents.base.BaseAgent method)
(rlpyt.agents.dqn.dqn_agent.DqnAgent method)
(rlpyt.agents.pg.gaussian.GaussianPgAgent method)
(rlpyt.agents.pg.gaussian.RecurrentGaussianPgAgentBase method)
(rlpyt.utils.collections.NamedTupleSchema method)
__contains__() (rlpyt.utils.collections.DocExampleNat method)
__getattr__() (rlpyt.utils.collections.NamedTuple method)
__getitem__() (rlpyt.utils.collections.DocExampleNat method)
__init__() (rlpyt.agents.base.BaseAgent method)
(rlpyt.agents.dqn.catdqn_agent.CatDqnAgent method)
(rlpyt.agents.dqn.epsilon_greedy.EpsilonGreedyAgentMixin method)
(rlpyt.agents.pg.atari.AtariFfAgent method)
(rlpyt.agents.pg.atari.AtariLstmAgent method)
(rlpyt.agents.pg.mujoco.MujocoFfAgent method)
(rlpyt.agents.pg.mujoco.MujocoLstmAgent method)
(rlpyt.agents.qpg.ddpg_agent.DdpgAgent method)
(rlpyt.agents.qpg.sac_agent.SacAgent method)
(rlpyt.agents.qpg.td3_agent.Td3Agent method)
(rlpyt.algos.dqn.cat_dqn.CategoricalDQN method)
(rlpyt.algos.dqn.dqn.DQN method)
(rlpyt.algos.dqn.r2d1.R2D1 method)
(rlpyt.algos.pg.a2c.A2C method)
(rlpyt.algos.pg.ppo.PPO method)
(rlpyt.algos.qpg.ddpg.DDPG method)
(rlpyt.algos.qpg.sac.SAC method)
(rlpyt.algos.qpg.td3.TD3 method)
(rlpyt.models.dqn.atari_catdqn_model.AtariCatDqnModel method)
(rlpyt.models.dqn.atari_dqn_model.AtariDqnModel method)
(rlpyt.models.dqn.atari_r2d1_model.AtariR2d1Model method)
(rlpyt.models.pg.atari_ff_model.AtariFfModel method)
(rlpyt.models.pg.atari_lstm_model.AtariLstmModel method)
(rlpyt.models.pg.mujoco_ff_model.MujocoFfModel method)
(rlpyt.models.pg.mujoco_lstm_model.MujocoLstmModel method)
(rlpyt.models.qpg.mlp.MuMlpModel method)
(rlpyt.models.qpg.mlp.QofMuMlpModel method)
(rlpyt.runners.minibatch_rl.MinibatchRl method)
(rlpyt.spaces.composite.Composite method)
(rlpyt.spaces.float_box.FloatBox method)
(rlpyt.spaces.gym_wrapper.GymSpaceWrapper method)
(rlpyt.spaces.int_box.IntBox method)
__setitem__() (rlpyt.utils.collections.DocExampleNat method)
_agent_init() (rlpyt.samplers.parallel.gpu.sampler.GpuSamplerBase method)
_asdict() (rlpyt.utils.collections.NamedTuple method)
_cross_variants() (in module rlpyt.utils.launching.variant)
_log_infos() (rlpyt.runners.minibatch_rl.MinibatchRlBase method)
_make() (rlpyt.utils.collections.NamedTuple method)
(rlpyt.utils.collections.NamedTupleSchema method)
_replace() (rlpyt.utils.collections.NamedTuple method)
A
A2C (class in rlpyt.algos.pg.a2c)
action_server_process() (rlpyt.samplers.async_.gpu_sampler.AsyncGpuSamplerBase method)
ActionServer (class in rlpyt.samplers.parallel.gpu.action_server)
add_exp_param() (in module rlpyt.utils.logging.context)
advance() (rlpyt.replays.sum_tree.SumTree method)
advance_rnn_state() (rlpyt.agents.base.RecurrentAgentMixin method)
advantage() (rlpyt.models.dqn.dueling.DuelingHeadModel method)
affinity_from_code() (in module rlpyt.utils.launching.affinity)
AlternatingActionServer (class in rlpyt.samplers.parallel.gpu.action_server)
AlternatingRecurrentAgentMixin (class in rlpyt.agents.base)
AlternatingRecurrentGaussianPgAgent (class in rlpyt.agents.pg.gaussian)
AlternatingSampler (class in rlpyt.samplers.parallel.gpu.alternating_sampler)
AlternatingSamplerBase (class in rlpyt.samplers.parallel.gpu.alternating_sampler)
append_samples() (rlpyt.replays.base.BaseReplayBuffer method)
(rlpyt.replays.frame.FrameBufferMixin method)
(rlpyt.replays.n_step.BaseNStepReturnBuffer method)
(rlpyt.replays.non_sequence.prioritized.PrioritizedReplay method)
(rlpyt.replays.sequence.n_step.SequenceNStepReturnBuffer method)
(rlpyt.replays.sequence.prioritized.PrioritizedSequenceReplay method)
async_cpu() (rlpyt.agents.base.BaseAgent method)
async_initialize() (rlpyt.algos.base.RlAlgorithm method)
(rlpyt.algos.dqn.dqn.DQN method)
(rlpyt.algos.qpg.ddpg.DDPG method)
(rlpyt.samplers.async_.base.AsyncSamplerMixin method)
AsyncActionServer (class in rlpyt.samplers.async_.action_server)
AsyncAlternatingActionServer (class in rlpyt.samplers.async_.action_server)
AsyncAlternatingSampler (class in rlpyt.samplers.async_.alternating_sampler)
AsyncAlternatingSamplerBase (class in rlpyt.samplers.async_.alternating_sampler)
AsyncCpuSampler (class in rlpyt.samplers.async_.cpu_sampler)
AsyncGpuSampler (class in rlpyt.samplers.async_.gpu_sampler)
AsyncGpuSamplerBase (class in rlpyt.samplers.async_.gpu_sampler)
AsyncNoOverlapAlternatingActionServer (class in rlpyt.samplers.async_.action_server)
AsyncNoOverlapAlternatingSampler (class in rlpyt.samplers.async_.alternating_sampler)
AsyncParallelSamplerMixin (class in rlpyt.samplers.async_.base)
AsyncPrioritizedReplayBuffer (class in rlpyt.replays.non_sequence.prioritized)
AsyncPrioritizedReplayFrameBuffer (class in rlpyt.replays.non_sequence.frame)
AsyncPrioritizedSequenceReplayBuffer (class in rlpyt.replays.sequence.prioritized)
AsyncPrioritizedSequenceReplayFrameBuffer (class in rlpyt.replays.sequence.frame)
AsyncReplayBufferMixin (class in rlpyt.replays.async_)
AsyncRl (class in rlpyt.runners.async_rl)
AsyncRlBase (class in rlpyt.runners.async_rl)
AsyncRlEval (class in rlpyt.runners.async_rl)
AsyncSamplerMixin (class in rlpyt.samplers.async_.base)
AsyncSerialSampler (class in rlpyt.samplers.async_.serial_sampler)
AsyncSumTree (class in rlpyt.replays.sum_tree)
AsyncTlPrioritizedReplayBuffer (class in rlpyt.replays.non_sequence.time_limit)
AsyncTlUniformReplayBuffer (class in rlpyt.replays.non_sequence.time_limit)
AsyncUniformReplayBuffer (class in rlpyt.replays.non_sequence.uniform)
AsyncUniformReplayFrameBuffer (class in rlpyt.replays.non_sequence.frame)
AsyncUniformSequenceReplayBuffer (class in rlpyt.replays.sequence.uniform)
AsyncUniformSequenceReplayFrameBuffer (class in rlpyt.replays.sequence.frame)
AtariCatDqnModel (class in rlpyt.models.dqn.atari_catdqn_model)
AtariDqnModel (class in rlpyt.models.dqn.atari_dqn_model)
AtariEnv (class in rlpyt.envs.atari.atari_env)
AtariFfAgent (class in rlpyt.agents.pg.atari)
AtariFfModel (class in rlpyt.models.pg.atari_ff_model)
AtariLstmAgent (class in rlpyt.agents.pg.atari)
AtariLstmModel (class in rlpyt.models.pg.atari_lstm_model)
AtariMixin (class in rlpyt.agents.pg.atari)
AtariR2d1Model (class in rlpyt.models.dqn.atari_r2d1_model)
AtariTrajInfo (class in rlpyt.envs.atari.atari_env)
AttrDict (class in rlpyt.utils.collections)
B
backward() (rlpyt.models.utils.ScaleGrad static method)
BaseAgent (class in rlpyt.agents.base)
BaseCollector (class in rlpyt.samplers.collectors)
BaseEvalCollector (class in rlpyt.samplers.collectors)
BaseNStepReturnBuffer (class in rlpyt.replays.n_step)
BaseReplayBuffer (class in rlpyt.replays.base)
BaseRunner (class in rlpyt.runners.base)
BaseSampler (class in rlpyt.samplers.base)
buffer_from_example() (in module rlpyt.utils.buffer)
buffer_func() (in module rlpyt.utils.buffer)
buffer_method() (in module rlpyt.utils.buffer)
buffer_to() (in module rlpyt.utils.buffer)
build_array() (in module rlpyt.utils.buffer)
build_ctrl() (rlpyt.runners.async_rl.AsyncRlBase method)
C
CatDqnAgent (class in rlpyt.agents.dqn.catdqn_agent)
Categorical (class in rlpyt.distributions.categorical)
CategoricalDQN (class in rlpyt.algos.dqn.cat_dqn)
CategoricalEpsilonGreedy (class in rlpyt.distributions.epsilon_greedy)
CategoricalPgAgent (class in rlpyt.agents.pg.categorical)
check_progress() (in module rlpyt.utils.logging.context)
collect_batch() (rlpyt.samplers.collectors.BaseCollector method)
collect_evaluation() (rlpyt.samplers.collectors.BaseEvalCollector method)
collector_initialize() (rlpyt.agents.dqn.epsilon_greedy.EpsilonGreedyAgentMixin method)
Composite (class in rlpyt.spaces.composite)
compute_input_priorities() (rlpyt.algos.dqn.r2d1.R2D1 method)
compute_returns() (rlpyt.replays.n_step.BaseNStepReturnBuffer method)
conv2d_output_shape() (in module rlpyt.models.utils)
Conv2dHeadModel (class in rlpyt.models.conv2d)
Conv2dModel (class in rlpyt.models.conv2d)
conv_out_size() (rlpyt.models.conv2d.Conv2dModel method)
convert() (rlpyt.spaces.gym_wrapper.GymSpaceWrapper method)
copy() (rlpyt.utils.collections.AttrDict method)
CpuEvalCollector (class in rlpyt.samplers.parallel.cpu.collectors)
CpuResetCollector (class in rlpyt.samplers.parallel.cpu.collectors)
CpuSampler (class in rlpyt.samplers.parallel.cpu.sampler)
CpuWaitResetCollector (class in rlpyt.samplers.parallel.cpu.collectors)
D
data_parallel() (rlpyt.agents.base.BaseAgent method)
DDPG (class in rlpyt.algos.qpg.ddpg)
DdpgAgent (class in rlpyt.agents.qpg.ddpg_agent)
DecorrelatingStartCollector (class in rlpyt.samplers.collectors)
discount_return() (in module rlpyt.algos.utils)
discount_return_n_step() (in module rlpyt.algos.utils)
discount_return_tl() (in module rlpyt.algos.utils)
DiscreteMixin (class in rlpyt.distributions.discrete)
Distribution (class in rlpyt.distributions.base)
DistributionalDuelingHeadModel (class in rlpyt.models.dqn.dueling)
DistributionalHeadModel (class in rlpyt.models.dqn.atari_catdqn_model)
DocExampleNat (class in rlpyt.utils.collections)
DQN (class in rlpyt.algos.dqn.dqn)
DqnAgent (class in rlpyt.agents.dqn.dqn_agent)
drain_queue() (in module rlpyt.utils.synchronize)
DuelingHeadModel (class in rlpyt.models.dqn.dueling)
E
empty() (in module rlpyt.utils.misc)
encode_affinity() (in module rlpyt.utils.launching.affinity)
,
[1]
entropy() (rlpyt.distributions.base.Distribution method)
(rlpyt.distributions.gaussian.Gaussian method)
Env (class in rlpyt.envs.base)
EnvInfoWrapper (class in rlpyt.envs.gym)
EpsilonGreedy (class in rlpyt.distributions.epsilon_greedy)
EpsilonGreedyAgentMixin (class in rlpyt.agents.dqn.epsilon_greedy)
eval_mode() (rlpyt.agents.base.BaseAgent method)
(rlpyt.agents.base.RecurrentAgentMixin method)
(rlpyt.agents.dqn.epsilon_greedy.EpsilonGreedyAgentMixin method)
evaluate_agent() (rlpyt.runners.minibatch_rl.MinibatchRlEval method)
(rlpyt.samplers.async_.cpu_sampler.AsyncCpuSampler method)
(rlpyt.samplers.async_.serial_sampler.AsyncSerialSampler method)
(rlpyt.samplers.base.BaseSampler method)
(rlpyt.samplers.parallel.base.ParallelSamplerBase method)
(rlpyt.samplers.parallel.cpu.sampler.CpuSampler method)
(rlpyt.samplers.parallel.gpu.sampler.GpuSamplerBase method)
(rlpyt.samplers.serial.sampler.SerialSampler method)
extract_batch() (rlpyt.replays.non_sequence.n_step.NStepReturnBuffer method)
(rlpyt.replays.sequence.n_step.SequenceNStepReturnBuffer method)
extract_observation() (rlpyt.replays.non_sequence.frame.NStepFrameBuffer method)
(rlpyt.replays.non_sequence.n_step.NStepReturnBuffer method)
(rlpyt.replays.sequence.frame.SequenceNStepFrameBuffer method)
extract_sequences() (in module rlpyt.utils.misc)
F
find_port() (in module rlpyt.utils.synchronize)
FloatBox (class in rlpyt.spaces.float_box)
forward() (rlpyt.models.conv2d.Conv2dHeadModel method)
(rlpyt.models.conv2d.Conv2dModel method)
(rlpyt.models.dqn.atari_catdqn_model.AtariCatDqnModel method)
(rlpyt.models.dqn.atari_dqn_model.AtariDqnModel method)
(rlpyt.models.dqn.dueling.DuelingHeadModel method)
(rlpyt.models.mlp.MlpModel method)
(rlpyt.models.pg.atari_ff_model.AtariFfModel method)
(rlpyt.models.pg.atari_lstm_model.AtariLstmModel method)
(rlpyt.models.pg.mujoco_ff_model.MujocoFfModel method)
(rlpyt.models.pg.mujoco_lstm_model.MujocoLstmModel method)
(rlpyt.models.utils.ScaleGrad static method)
FrameBufferMixin (class in rlpyt.replays.frame)
from_onehot() (in module rlpyt.utils.tensor)
(rlpyt.distributions.discrete.DiscreteMixin method)
G
Gaussian (class in rlpyt.distributions.gaussian)
GaussianPgAgent (class in rlpyt.agents.pg.gaussian)
generalized_advantage_estimation() (in module rlpyt.algos.utils)
generalized_advantage_estimation_tl() (in module rlpyt.algos.utils)
get() (rlpyt.utils.collections.DocExampleNat method)
get_itr_snapshot() (rlpyt.runners.minibatch_rl.MinibatchRlBase method)
get_leading_dims() (in module rlpyt.utils.buffer)
get_n_itr() (rlpyt.runners.minibatch_rl.MinibatchRlBase method)
get_traj_info_kwargs() (rlpyt.runners.minibatch_rl.MinibatchRlBase method)
GpuEvalCollector (class in rlpyt.samplers.parallel.gpu.collectors)
GpuResetCollector (class in rlpyt.samplers.parallel.gpu.collectors)
GpuSampler (class in rlpyt.samplers.parallel.gpu.sampler)
GpuSamplerBase (class in rlpyt.samplers.parallel.gpu.sampler)
GpuWaitResetCollector (class in rlpyt.samplers.parallel.gpu.collectors)
GymEnvWrapper (class in rlpyt.envs.gym)
GymSpaceWrapper (class in rlpyt.spaces.gym_wrapper)
I
infer_leading_dims() (in module rlpyt.utils.array)
(in module rlpyt.utils.tensor)
initialize() (rlpyt.agents.base.BaseAgent method)
(rlpyt.agents.dqn.dqn_agent.DqnAgent method)
(rlpyt.agents.pg.gaussian.GaussianPgAgent method)
(rlpyt.agents.qpg.ddpg_agent.DdpgAgent method)
(rlpyt.algos.base.RlAlgorithm method)
(rlpyt.algos.dqn.dqn.DQN method)
(rlpyt.algos.pg.base.PolicyGradientAlgo method)
(rlpyt.algos.pg.ppo.PPO method)
(rlpyt.algos.qpg.ddpg.DDPG method)
(rlpyt.algos.qpg.sac.SAC method)
(rlpyt.samplers.async_.cpu_sampler.AsyncCpuSampler method)
(rlpyt.samplers.async_.gpu_sampler.AsyncGpuSamplerBase method)
(rlpyt.samplers.async_.serial_sampler.AsyncSerialSampler method)
(rlpyt.samplers.base.BaseSampler method)
(rlpyt.samplers.parallel.base.ParallelSamplerBase method)
(rlpyt.samplers.parallel.gpu.alternating_sampler.AlternatingSamplerBase method)
(rlpyt.samplers.serial.sampler.SerialSampler method)
initialize_replay_buffer() (rlpyt.algos.dqn.dqn.DQN method)
(rlpyt.algos.dqn.r2d1.R2D1 method)
(rlpyt.algos.qpg.ddpg.DDPG method)
(rlpyt.algos.qpg.sac.SAC method)
initialize_worker() (in module rlpyt.samplers.parallel.worker)
IntBox (class in rlpyt.spaces.int_box)
inv_value_scale() (rlpyt.algos.dqn.r2d1.R2D1 method)
is_namedarraytuple() (in module rlpyt.utils.collections)
is_namedarraytuple_class() (in module rlpyt.utils.collections)
is_namedtuple() (in module rlpyt.utils.collections)
is_namedtuple_class() (in module rlpyt.utils.collections)
items() (rlpyt.utils.collections.DocExampleNat method)
iterate_mb_idxs() (in module rlpyt.utils.misc)
K
kl() (rlpyt.distributions.base.Distribution method)
L
launch_experiment() (in module rlpyt.utils.launching.exp_launcher)
launch_memcpy() (rlpyt.runners.async_rl.AsyncRlBase method)
launch_optimizer_workers() (rlpyt.runners.async_rl.AsyncRlBase method)
launch_workers() (rlpyt.runners.sync_rl.SyncRlMixin method)
likelihood_ratio() (rlpyt.distributions.base.Distribution method)
load_optim_state_dict() (rlpyt.algos.base.RlAlgorithm method)
load_state_dict() (rlpyt.agents.base.BaseAgent method)
load_variant() (in module rlpyt.utils.launching.variant)
log_diagnostics() (rlpyt.runners.minibatch_rl.MinibatchRlBase method)
log_likelihood() (rlpyt.distributions.base.Distribution method)
(rlpyt.distributions.gaussian.Gaussian method)
logger_context() (in module rlpyt.utils.logging.context)
loss() (rlpyt.algos.dqn.cat_dqn.CategoricalDQN method)
(rlpyt.algos.dqn.dqn.DQN method)
(rlpyt.algos.dqn.r2d1.R2D1 method)
(rlpyt.algos.pg.a2c.A2C method)
(rlpyt.algos.pg.ppo.PPO method)
(rlpyt.algos.qpg.sac.SAC method)
M
make() (in module rlpyt.envs.gym)
make_affinity() (in module rlpyt.utils.launching.affinity)
make_env_to_model_kwargs() (rlpyt.agents.base.BaseAgent method)
(rlpyt.agents.pg.atari.AtariMixin method)
(rlpyt.agents.pg.mujoco.MujocoMixin method)
make_seed() (in module rlpyt.utils.seed)
make_variants() (in module rlpyt.utils.launching.variant)
make_vec_eps() (rlpyt.agents.dqn.epsilon_greedy.EpsilonGreedyAgentMixin method)
mean_entropy() (rlpyt.distributions.base.Distribution method)
mean_kl() (rlpyt.distributions.base.Distribution method)
mean_perplexity() (rlpyt.distributions.base.Distribution method)
memory_copier() (in module rlpyt.runners.async_rl)
MinibatchRl (class in rlpyt.runners.minibatch_rl)
MinibatchRlBase (class in rlpyt.runners.minibatch_rl)
MinibatchRlEval (class in rlpyt.runners.minibatch_rl)
MlpModel (class in rlpyt.models.mlp)
mu_loss() (rlpyt.algos.qpg.ddpg.DDPG method)
MujocoFfAgent (class in rlpyt.agents.pg.mujoco)
MujocoFfModel (class in rlpyt.models.pg.mujoco_ff_model)
MujocoLstmAgent (class in rlpyt.agents.pg.mujoco)
MujocoLstmModel (class in rlpyt.models.pg.mujoco_lstm_model)
MujocoMixin (class in rlpyt.agents.pg.mujoco)
MuMlpModel (class in rlpyt.models.qpg.mlp)
N
n (rlpyt.spaces.int_box.IntBox attribute)
NamedArrayTuple (class in rlpyt.utils.collections)
namedarraytuple() (in module rlpyt.utils.collections)
namedarraytuple_like() (in module rlpyt.utils.collections)
NamedArrayTupleSchema (class in rlpyt.utils.collections)
NamedArrayTupleSchema_like() (in module rlpyt.utils.collections)
NamedTuple (class in rlpyt.utils.collections)
NamedTupleSchema (class in rlpyt.utils.collections)
names (rlpyt.spaces.composite.Composite attribute)
NoOverlapAlternatingActionServer (class in rlpyt.samplers.parallel.gpu.action_server)
NoOverlapAlternatingSampler (class in rlpyt.samplers.parallel.gpu.alternating_sampler)
np_mp_array() (in module rlpyt.utils.buffer)
NStepFrameBuffer (class in rlpyt.replays.non_sequence.frame)
NStepReturnBuffer (class in rlpyt.replays.non_sequence.n_step)
NStepTimeLimitBuffer (class in rlpyt.replays.non_sequence.time_limit)
null_value() (rlpyt.spaces.base.Space method)
(rlpyt.spaces.composite.Composite method)
(rlpyt.spaces.gym_wrapper.GymSpaceWrapper method)
numpify_buffer() (in module rlpyt.utils.buffer)
O
obtain_samples() (rlpyt.samplers.async_.base.AsyncParallelSamplerMixin method)
(rlpyt.samplers.async_.cpu_sampler.AsyncCpuSampler method)
(rlpyt.samplers.async_.serial_sampler.AsyncSerialSampler method)
(rlpyt.samplers.base.BaseSampler method)
(rlpyt.samplers.parallel.base.ParallelSamplerBase method)
(rlpyt.samplers.parallel.cpu.sampler.CpuSampler method)
(rlpyt.samplers.parallel.gpu.sampler.GpuSamplerBase method)
(rlpyt.samplers.serial.sampler.SerialSampler method)
optim_initialize() (rlpyt.algos.base.RlAlgorithm method)
(rlpyt.algos.dqn.dqn.DQN method)
(rlpyt.algos.qpg.ddpg.DDPG method)
(rlpyt.algos.qpg.sac.SAC method)
optim_startup() (rlpyt.runners.async_rl.AsyncRlBase method)
optim_state_dict() (rlpyt.algos.base.RlAlgorithm method)
optimize_agent() (rlpyt.algos.base.RlAlgorithm method)
(rlpyt.algos.dqn.dqn.DQN method)
(rlpyt.algos.dqn.r2d1.R2D1 method)
(rlpyt.algos.pg.a2c.A2C method)
(rlpyt.algos.pg.ppo.PPO method)
(rlpyt.algos.qpg.ddpg.DDPG method)
(rlpyt.algos.qpg.sac.SAC method)
output_size (rlpyt.models.conv2d.Conv2dHeadModel attribute)
(rlpyt.models.mlp.MlpModel attribute)
P
ParallelSamplerBase (class in rlpyt.samplers.parallel.base)
perplexity() (rlpyt.distributions.base.Distribution method)
pi() (rlpyt.agents.qpg.sac_agent.SacAgent method)
PiMlpModel (class in rlpyt.models.qpg.mlp)
PolicyGradientAlgo (class in rlpyt.algos.pg.base)
PPO (class in rlpyt.algos.pg.ppo)
print_tree() (rlpyt.replays.sum_tree.SumTree method)
PrioritizedReplay (class in rlpyt.replays.non_sequence.prioritized)
PrioritizedReplayBuffer (class in rlpyt.replays.non_sequence.prioritized)
PrioritizedReplayFrameBuffer (class in rlpyt.replays.non_sequence.frame)
PrioritizedSequenceReplay (class in rlpyt.replays.sequence.prioritized)
PrioritizedSequenceReplayBuffer (class in rlpyt.replays.sequence.prioritized)
PrioritizedSequenceReplayFrameBuffer (class in rlpyt.replays.sequence.frame)
process_returns() (rlpyt.algos.pg.base.PolicyGradientAlgo method)
ProgBarCounter (class in rlpyt.utils.prog_bar)
Q
q() (rlpyt.agents.qpg.ddpg_agent.DdpgAgent method)
(rlpyt.agents.qpg.sac_agent.SacAgent method)
(rlpyt.agents.qpg.td3_agent.Td3Agent method)
q_at_mu() (rlpyt.agents.qpg.ddpg_agent.DdpgAgent method)
q_loss() (rlpyt.algos.qpg.ddpg.DDPG method)
(rlpyt.algos.qpg.td3.TD3 method)
QofMuMlpModel (class in rlpyt.models.qpg.mlp)
R
R2D1 (class in rlpyt.algos.dqn.r2d1)
R2d1Agent (class in rlpyt.agents.dqn.r2d1_agent)
R2d1AgentBase (class in rlpyt.agents.dqn.r2d1_agent)
RecurrentAgentMixin (class in rlpyt.agents.base)
RecurrentGaussianPgAgent (class in rlpyt.agents.pg.gaussian)
RecurrentGaussianPgAgentBase (class in rlpyt.agents.pg.gaussian)
recv_shared_memory() (rlpyt.agents.base.BaseAgent method)
reset() (rlpyt.agents.base.RecurrentAgentMixin method)
(rlpyt.envs.atari.atari_env.AtariEnv method)
(rlpyt.envs.base.Env method)
(rlpyt.envs.gym.GymEnvWrapper method)
reset_if_needed() (rlpyt.samplers.collectors.BaseCollector method)
reset_one() (rlpyt.agents.base.RecurrentAgentMixin method)
restore_leading_dims() (in module rlpyt.utils.tensor)
revert() (rlpyt.spaces.gym_wrapper.GymSpaceWrapper method)
RlAlgorithm (class in rlpyt.algos.base)
run_async_sampler() (in module rlpyt.runners.async_rl)
run_async_sampler_eval() (in module rlpyt.runners.async_rl)
run_experiments() (in module rlpyt.utils.launching.exp_launcher)
RWLock (class in rlpyt.utils.synchronize)
S
SAC (class in rlpyt.algos.qpg.sac)
SacAgent (class in rlpyt.agents.qpg.sac_agent)
sample() (rlpyt.distributions.base.Distribution method)
(rlpyt.distributions.categorical.Categorical method)
(rlpyt.distributions.epsilon_greedy.CategoricalEpsilonGreedy method)
(rlpyt.distributions.epsilon_greedy.EpsilonGreedy method)
(rlpyt.distributions.gaussian.Gaussian method)
(rlpyt.replays.sum_tree.SumTree method)
(rlpyt.spaces.base.Space method)
(rlpyt.spaces.composite.Composite method)
(rlpyt.spaces.float_box.FloatBox method)
(rlpyt.spaces.gym_wrapper.GymSpaceWrapper method)
(rlpyt.spaces.int_box.IntBox method)
sample_batch() (rlpyt.replays.base.BaseReplayBuffer method)
(rlpyt.replays.non_sequence.prioritized.PrioritizedReplay method)
(rlpyt.replays.non_sequence.uniform.UniformReplay method)
(rlpyt.replays.sequence.prioritized.PrioritizedSequenceReplay method)
(rlpyt.replays.sequence.uniform.UniformSequenceReplay method)
sample_idxs() (rlpyt.replays.non_sequence.uniform.UniformReplay method)
(rlpyt.replays.sequence.uniform.UniformSequenceReplay method)
sample_loglikelihood() (rlpyt.distributions.gaussian.Gaussian method)
sample_mode() (rlpyt.agents.base.BaseAgent method)
(rlpyt.agents.base.RecurrentAgentMixin method)
(rlpyt.agents.dqn.epsilon_greedy.EpsilonGreedyAgentMixin method)
samples_to_buffer() (rlpyt.algos.dqn.dqn.DQN method)
(rlpyt.algos.qpg.ddpg.DDPG method)
(rlpyt.algos.qpg.sac.SAC method)
sampling_process() (in module rlpyt.samplers.parallel.worker)
save__init__args() (in module rlpyt.utils.quick_args)
save_itr_snapshot() (rlpyt.runners.minibatch_rl.MinibatchRlBase method)
save_variant() (in module rlpyt.utils.launching.variant)
ScaleGrad (class in rlpyt.models.utils)
select_at_indexes() (in module rlpyt.utils.array)
(in module rlpyt.utils.tensor)
send_shared_memory() (rlpyt.agents.base.BaseAgent method)
SequenceNStepFrameBuffer (class in rlpyt.replays.sequence.frame)
SequenceNStepReturnBuffer (class in rlpyt.replays.sequence.n_step)
SerialSampler (class in rlpyt.samplers.serial.sampler)
serve_actions() (rlpyt.samplers.parallel.gpu.action_server.ActionServer method)
serve_actions_evaluation() (rlpyt.samplers.async_.action_server.AsyncActionServer method)
(rlpyt.samplers.async_.action_server.AsyncAlternatingActionServer method)
(rlpyt.samplers.async_.action_server.AsyncNoOverlapAlternatingActionServer method)
(rlpyt.samplers.parallel.gpu.action_server.ActionServer method)
set_clip() (rlpyt.distributions.gaussian.Gaussian method)
set_epsilon() (rlpyt.distributions.epsilon_greedy.EpsilonGreedy method)
set_noise_clip() (rlpyt.distributions.gaussian.Gaussian method)
set_seed() (in module rlpyt.utils.seed)
set_squash() (rlpyt.distributions.gaussian.Gaussian method)
set_std() (rlpyt.distributions.gaussian.Gaussian method)
set_z() (rlpyt.distributions.epsilon_greedy.CategoricalEpsilonGreedy method)
shape (rlpyt.spaces.composite.Composite attribute)
Space (class in rlpyt.spaces.base)
spaces (rlpyt.envs.gym.GymEnvWrapper attribute)
(rlpyt.spaces.composite.Composite attribute)
start_agent() (rlpyt.samplers.collectors.BaseCollector method)
start_envs() (rlpyt.samplers.collectors.BaseCollector method)
(rlpyt.samplers.collectors.DecorrelatingStartCollector method)
startup() (rlpyt.runners.async_rl.AsyncRlBase method)
(rlpyt.runners.minibatch_rl.MinibatchRlBase method)
state_dict() (rlpyt.agents.base.BaseAgent method)
step() (rlpyt.agents.base.BaseAgent method)
(rlpyt.agents.dqn.catdqn_agent.CatDqnAgent method)
(rlpyt.agents.dqn.dqn_agent.DqnAgent method)
(rlpyt.agents.dqn.r2d1_agent.R2d1AgentBase method)
(rlpyt.agents.pg.gaussian.GaussianPgAgent method)
(rlpyt.agents.pg.gaussian.RecurrentGaussianPgAgentBase method)
(rlpyt.agents.qpg.ddpg_agent.DdpgAgent method)
(rlpyt.envs.base.Env method)
(rlpyt.envs.gym.EnvInfoWrapper method)
(rlpyt.envs.gym.GymEnvWrapper method)
store_diagnostics() (rlpyt.runners.minibatch_rl.MinibatchRlBase method)
strip_ddp_state_dict() (in module rlpyt.models.utils)
SumTree (class in rlpyt.replays.sum_tree)
sync_shared_memory() (rlpyt.agents.base.BaseAgent method)
SyncRl (class in rlpyt.runners.sync_rl)
SyncRlEval (class in rlpyt.runners.sync_rl)
SyncRlMixin (class in rlpyt.runners.sync_rl)
T
target() (rlpyt.agents.dqn.dqn_agent.DqnAgent method)
target_q() (rlpyt.agents.qpg.sac_agent.SacAgent method)
target_q_at_mu() (rlpyt.agents.qpg.ddpg_agent.DdpgAgent method)
(rlpyt.agents.qpg.td3_agent.Td3Agent method)
TD3 (class in rlpyt.algos.qpg.td3)
Td3Agent (class in rlpyt.agents.qpg.td3_agent)
TlPrioritizedReplayBuffer (class in rlpyt.replays.non_sequence.time_limit)
TlUniformReplayBuffer (class in rlpyt.replays.non_sequence.time_limit)
to_device() (rlpyt.agents.base.BaseAgent method)
to_onehot() (in module rlpyt.utils.array)
(in module rlpyt.utils.tensor)
(rlpyt.distributions.discrete.DiscreteMixin method)
torchify_buffer() (in module rlpyt.utils.buffer)
train() (rlpyt.runners.async_rl.AsyncRlBase method)
(rlpyt.runners.base.BaseRunner method)
(rlpyt.runners.minibatch_rl.MinibatchRl method)
(rlpyt.runners.minibatch_rl.MinibatchRlEval method)
train_mode() (rlpyt.agents.base.BaseAgent method)
(rlpyt.agents.base.RecurrentAgentMixin method)
U
UniformReplay (class in rlpyt.replays.non_sequence.uniform)
UniformReplayBuffer (class in rlpyt.replays.non_sequence.uniform)
UniformReplayFrameBuffer (class in rlpyt.replays.non_sequence.frame)
UniformSequenceReplay (class in rlpyt.replays.sequence.uniform)
UniformSequenceReplayBuffer (class in rlpyt.replays.sequence.uniform)
UniformSequenceReplayFrameBuffer (class in rlpyt.replays.sequence.frame)
update_batch_priorities() (rlpyt.replays.non_sequence.prioritized.PrioritizedReplay method)
(rlpyt.replays.sum_tree.SumTree method)
update_config() (in module rlpyt.utils.launching.variant)
update_state_dict() (in module rlpyt.models.utils)
update_target() (rlpyt.agents.dqn.dqn_agent.DqnAgent method)
V
valid_from_done() (in module rlpyt.algos.utils)
valid_mean() (in module rlpyt.utils.array)
(in module rlpyt.utils.tensor)
value() (rlpyt.agents.pg.gaussian.GaussianPgAgent method)
(rlpyt.agents.pg.gaussian.RecurrentGaussianPgAgentBase method)
value_scale() (rlpyt.algos.dqn.r2d1.R2D1 method)
VariantLevel (class in rlpyt.utils.launching.variant)
Z
zeros() (in module rlpyt.utils.misc)
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
.