Index

_

__add__() (Batch method) __call__() (ContinuousQFunction method) (ContinuousQuantileFunction method) (ContinuousVFunction method) (Critic method) (DeltaOrthogonal method) (DeterministicPolicy method) (DoubleCritic method) (MLP method), [1] (Model method) (MultiQuantileCritic method) (QuantileCritic method) (StateDependentGaussianPolicy method) (StateIndependentGaussianPolicy method) (Temperature method)

__mul__() (Batch method)

A

action_space (ResetDoneWrapper property) actions (Batch attribute) activations (Critic attribute) (DoubleCritic attribute) (MLP attribute) ActorCriticMixIn (class in xpag.agents.rljax_agents.algorithm.base_class.actor_critic) add_noise() (in module xpag.agents.rljax_agents.util.preprocess)

Agent (class in xpag.agents.agent) agent_factory() (in module xpag.agents.all_agents) apply() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method)

B

BaseAlgorithm (class in xpag.agents.rljax_agents.algorithm.base_class.base_algorithm) Batch (class in xpag.agents.flax_agents.sac.sac_from_jaxrl) bind() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method)

brax_notebook_replay() (in module xpag.tools.replay) Buffer (class in xpag.buffers.buffer)

C

calculate_kl_divergence() (in module xpag.agents.rljax_agents.util.distribution) call() (CumulRewardWrapper method) (GoalEnvWrapper method) call_async() (CumulRewardWrapper method) (GoalEnvWrapper method) call_wait() (CumulRewardWrapper method) (GoalEnvWrapper method) class_name() (ResetDoneWrapper class method) clip_gradient() (in module xpag.agents.rljax_agents.util.optim) clip_gradient_norm() (in module xpag.agents.rljax_agents.util.optim) clone() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method)

close() (CumulRewardWrapper method) (GoalEnvWrapper method) (ResetDoneWrapper method) close_extras() (CumulRewardWrapper method) (GoalEnvWrapper method) CompositeSetter (class in xpag.setters.setter) ContinuousQFunction (class in xpag.agents.rljax_agents.network.critic) ContinuousQuantileFunction (class in xpag.agents.rljax_agents.network.critic) ContinuousVFunction (class in xpag.agents.rljax_agents.network.critic) count() (Batch method) Critic (class in xpag.agents.flax_agents.sac.sac_from_jaxrl) CumulRewardWrapper (class in xpag.wrappers.goalenv_wrapper)

D

DataType (class in xpag.tools.utils) datatype_convert() (in module xpag.tools.utils) DDPG (class in xpag.agents.rljax_agents.algorithm.ddpg) default_init() (in module xpag.agents.flax_agents.sac.sac_from_jaxrl) DefaultBuffer (class in xpag.buffers.buffer) DefaultEpisodicBuffer (class in xpag.buffers.buffer) DefaultEpisodicSampler (class in xpag.samplers.sampler)

DefaultSampler (class in xpag.samplers.sampler) DefaultSetter (class in xpag.setters.setter) DeltaOrthogonal (class in xpag.agents.rljax_agents.network.initializer) DeterministicPolicy (class in xpag.agents.rljax_agents.network.actor) DisCorMixIn (class in xpag.agents.rljax_agents.algorithm.misc.discor_mixin) DoubleCritic (class in xpag.agents.flax_agents.sac.sac_from_jaxrl) DummyBuffer (class in xpag.agents.rljax_agents.rljax_interface)

E

EpisodicBuffer (class in xpag.buffers.buffer) eval_log() (in module xpag.tools.logging)

eval_log_reset() (in module xpag.tools.logging) evaluate_gaussian_and_tanh_log_prob() (in module xpag.agents.rljax_agents.util.distribution)

F

fake_action() (in module xpag.agents.rljax_agents.util.input) fake_state() (in module xpag.agents.rljax_agents.util.input) FeedForwardModel (class in xpag.agents.flax_agents.sdqn.sdqn) (class in xpag.agents.flax_agents.td3.td3) filter() (LevelFilter method)

FlaxSAC (class in xpag.agents.flax_agents.sac.sac) FlaxSDQN (class in xpag.agents.flax_agents.sdqn.sdqn) FlaxSDQNSetter (class in xpag.agents.flax_agents.sdqn.sdqn) FlaxTD3 (class in xpag.agents.flax_agents.td3.td3) FlaxTQC (class in xpag.agents.flax_agents.tqc.tqc)

G

gaussian_and_tanh_log_prob() (in module xpag.agents.rljax_agents.util.distribution) gaussian_log_prob() (in module xpag.agents.rljax_agents.util.distribution) get_attr() (CumulRewardWrapper method) (GoalEnvWrapper method) get_datatype() (in module xpag.tools.utils) get_env_dimensions() (in module xpag.tools.utils) get_q_at_action() (in module xpag.agents.rljax_agents.util.preprocess) get_quantile_at_action() (in module xpag.agents.rljax_agents.util.preprocess) get_variable() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method)

get_wrapper_attr() (CumulRewardWrapper method) (GoalEnvWrapper method) (ResetDoneWrapper method) GoalEnvWrapper (class in xpag.wrappers.goalenv_wrapper)

H

has_rng() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method) has_variable() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method)

hstack() (in module xpag.tools.utils) huber() (in module xpag.agents.flax_agents.tqc.tqc) (in module xpag.agents.rljax_agents.util.loss)

I

index() (Batch method) init() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method) init_rp_buffer() (JaxBuffer method) init_with_output() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method) insert() (Buffer method) (DefaultBuffer method) (DefaultEpisodicBuffer method) (EpisodicBuffer method) (JaxBuffer method) (RBQueue method) (RljaxBuffer method)

is_initializing() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method) is_mutable_collection() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method)

J

JaxBuffer (class in xpag.buffers.jax_buffer)

JaxSampler (class in xpag.samplers.jax_sampler)

L

lazy_init() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method)

LevelFilter (class in xpag.tools.logging) load_params() (in module xpag.agents.rljax_agents.util.saving) logical_or() (in module xpag.tools.utils)

M

make_rng() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method) masks (Batch attribute) maximum() (in module xpag.tools.utils) metadata (ResetDoneWrapper property) MLP (class in xpag.agents.flax_agents.sac.sac_from_jaxrl) (class in xpag.agents.rljax_agents.network.base) Model (class in xpag.agents.flax_agents.sac.sac_from_jaxrl) module xpag.agents xpag.agents.agent xpag.agents.all_agents xpag.agents.flax_agents xpag.agents.flax_agents.sac xpag.agents.flax_agents.sac.sac xpag.agents.flax_agents.sac.sac_from_jaxrl xpag.agents.flax_agents.sdqn xpag.agents.flax_agents.sdqn.sdqn xpag.agents.flax_agents.td3 xpag.agents.flax_agents.td3.td3 xpag.agents.flax_agents.tqc xpag.agents.flax_agents.tqc.tqc xpag.agents.rljax_agents xpag.agents.rljax_agents.algorithm xpag.agents.rljax_agents.algorithm.base_class xpag.agents.rljax_agents.algorithm.base_class.actor_critic xpag.agents.rljax_agents.algorithm.base_class.base_algorithm xpag.agents.rljax_agents.algorithm.ddpg xpag.agents.rljax_agents.algorithm.misc xpag.agents.rljax_agents.algorithm.misc.discor_mixin xpag.agents.rljax_agents.algorithm.sac xpag.agents.rljax_agents.algorithm.sac_discor xpag.agents.rljax_agents.algorithm.td3 xpag.agents.rljax_agents.algorithm.tqc xpag.agents.rljax_agents.network xpag.agents.rljax_agents.network.actor xpag.agents.rljax_agents.network.base xpag.agents.rljax_agents.network.critic xpag.agents.rljax_agents.network.initializer xpag.agents.rljax_agents.rljax_interface xpag.agents.rljax_agents.util xpag.agents.rljax_agents.util.distribution xpag.agents.rljax_agents.util.input xpag.agents.rljax_agents.util.loss xpag.agents.rljax_agents.util.optim xpag.agents.rljax_agents.util.preprocess xpag.agents.rljax_agents.util.saving xpag.buffers xpag.buffers.buffer xpag.buffers.jax_buffer xpag.buffers.rljax_buffer xpag.plotting xpag.plotting.plotting xpag.samplers xpag.samplers.HER xpag.samplers.jax_sampler xpag.samplers.sampler xpag.setters xpag.setters.setter xpag.tools xpag.tools.eval xpag.tools.learn xpag.tools.logging xpag.tools.replay xpag.tools.timing xpag.tools.utils xpag.wrappers xpag.wrappers.brax_vec_env xpag.wrappers.goalenv_wrapper xpag.wrappers.gym_vec_env xpag.wrappers.reset_done

mujoco_notebook_replay() (in module xpag.tools.replay) MultiQuantileCritic (class in xpag.agents.flax_agents.tqc.tqc)

N

next_observations (Batch attribute) np_random (CumulRewardWrapper property) (GoalEnvWrapper property) (ResetDoneWrapper property)

NStepBuffer (class in xpag.buffers.rljax_buffer)

O

observation_space (ResetDoneWrapper property) observations (Batch attribute)

OffPolicyActorCritic (class in xpag.agents.rljax_agents.algorithm.base_class.actor_critic) OffPolicyAlgorithm (class in xpag.agents.rljax_agents.algorithm.base_class.base_algorithm) optimize() (in module xpag.agents.rljax_agents.util.optim)

P

param() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method) params_dict() (ContinuousQFunction method) (ContinuousQuantileFunction method) (ContinuousVFunction method) (DeterministicPolicy method) (MLP method) (StateDependentGaussianPolicy method) (StateIndependentGaussianPolicy method)

perturb() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method) preprocess_state() (in module xpag.agents.rljax_agents.util.preprocess) put_variable() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method)

Q

quantile_loss() (in module xpag.agents.flax_agents.tqc.tqc) (in module xpag.agents.rljax_agents.util.loss)

QuantileCritic (class in xpag.agents.flax_agents.tqc.tqc)

R

RBQueue (class in xpag.buffers.jax_buffer) RBUniformSampling (class in xpag.samplers.jax_sampler) render() (CumulRewardWrapper method) (GoalEnvWrapper method) (ResetDoneWrapper method) render_mode (ResetDoneWrapper property) reparameterize_gaussian() (in module xpag.agents.rljax_agents.util.distribution) reparameterize_gaussian_and_tanh() (in module xpag.agents.rljax_agents.util.distribution) replace() (Model method) (ReplayBufferState method) (TrainingState method), [1] ReplayBuffer (class in xpag.buffers.rljax_buffer) ReplayBufferState (class in xpag.samplers.jax_sampler)

reset() (CumulRewardWrapper method) (GoalEnvWrapper method) (ResetDoneWrapper method) reset_async() (CumulRewardWrapper method) (GoalEnvWrapper method) reset_wait() (CumulRewardWrapper method) (GoalEnvWrapper method) ResetDoneWrapper (class in xpag.wrappers.reset_done) reshape() (in module xpag.tools.utils) reward_range (ResetDoneWrapper property) rewards (Batch attribute) RljaxBuffer (class in xpag.buffers.rljax_buffer) RljaxSAC (class in xpag.agents.rljax_agents.rljax_interface)

S

SAC (class in xpag.agents.rljax_agents.algorithm.sac) (in module xpag.agents.all_agents) SACDisCor (class in xpag.agents.rljax_agents.algorithm.sac_discor) SACLearner (class in xpag.agents.flax_agents.sac.sac_from_jaxrl) sample() (Buffer method) (DefaultBuffer method) (DefaultEpisodicBuffer method) (DefaultEpisodicSampler method) (DefaultSampler method) (EpisodicBuffer method) (JaxBuffer method) (JaxSampler method) (RBUniformSampling method) (RljaxBuffer method) (Sampler method) sample_actions() (in module xpag.agents.flax_agents.sac.sac_from_jaxrl) Sampler (class in xpag.samplers.sampler) save_params() (in module xpag.agents.rljax_agents.util.saving) SaveEpisode (class in xpag.tools.eval) set_attr() (CumulRewardWrapper method) (GoalEnvWrapper method) Setter (class in xpag.setters.setter) setup() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method)

single_episode_plot() (in module xpag.plotting.plotting) single_rollout_eval() (in module xpag.tools.eval) soft_update() (in module xpag.agents.rljax_agents.util.optim) sow() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method) spec (ResetDoneWrapper property) squeeze() (in module xpag.tools.utils) state_dict() (ContinuousQFunction method) (ContinuousQuantileFunction method) (ContinuousVFunction method) (DeterministicPolicy method) (MLP method) (StateDependentGaussianPolicy method) (StateIndependentGaussianPolicy method) StateDependentGaussianPolicy (class in xpag.agents.rljax_agents.network.actor) StateIndependentGaussianPolicy (class in xpag.agents.rljax_agents.network.actor) step() (CumulRewardWrapper method) (GoalEnvWrapper method) (ResetDoneWrapper method) step_async() (CumulRewardWrapper method) (GoalEnvWrapper method) step_wait() (CumulRewardWrapper method) (GoalEnvWrapper method) store_done() (DefaultEpisodicBuffer method) (EpisodicBuffer method)

T

tabulate() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method) target_update() (in module xpag.agents.flax_agents.sac.sac_from_jaxrl)

TD3 (class in xpag.agents.rljax_agents.algorithm.td3) Temperature (class in xpag.agents.flax_agents.sac.sac_from_jaxrl) TQC (class in xpag.agents.rljax_agents.algorithm.tqc) TQCLearner (class in xpag.agents.flax_agents.tqc.tqc) TrainingState (class in xpag.agents.flax_agents.sdqn.sdqn) (class in xpag.agents.flax_agents.td3.td3) tree_sum() (in module xpag.tools.utils)

U

unbind() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method) unwrapped (CumulRewardWrapper property) (GoalEnvWrapper property) (ResetDoneWrapper property)

update_actor() (in module xpag.agents.flax_agents.sac.sac_from_jaxrl) (in module xpag.agents.flax_agents.tqc.tqc) update_critic() (in module xpag.agents.flax_agents.sac.sac_from_jaxrl) (in module xpag.agents.flax_agents.tqc.tqc) update_temperature() (in module xpag.agents.flax_agents.sac.sac_from_jaxrl)

V

variable() (Critic method) (DoubleCritic method) (MLP method) (MultiQuantileCritic method) (QuantileCritic method) (Temperature method)

variables (Critic property) (DoubleCritic property) (MLP property) (MultiQuantileCritic property) (QuantileCritic property) (Temperature property)

W

weight_decay() (in module xpag.agents.rljax_agents.util.optim)

where() (in module xpag.tools.utils) wrapper_spec() (ResetDoneWrapper class method)

X

xpag.agents module xpag.agents.agent module xpag.agents.all_agents module xpag.agents.flax_agents module xpag.agents.flax_agents.sac module xpag.agents.flax_agents.sac.sac module xpag.agents.flax_agents.sac.sac_from_jaxrl module xpag.agents.flax_agents.sdqn module xpag.agents.flax_agents.sdqn.sdqn module xpag.agents.flax_agents.td3 module xpag.agents.flax_agents.td3.td3 module xpag.agents.flax_agents.tqc module xpag.agents.flax_agents.tqc.tqc module xpag.agents.rljax_agents module xpag.agents.rljax_agents.algorithm module xpag.agents.rljax_agents.algorithm.base_class module xpag.agents.rljax_agents.algorithm.base_class.actor_critic module xpag.agents.rljax_agents.algorithm.base_class.base_algorithm module xpag.agents.rljax_agents.algorithm.ddpg module xpag.agents.rljax_agents.algorithm.misc module xpag.agents.rljax_agents.algorithm.misc.discor_mixin module xpag.agents.rljax_agents.algorithm.sac module xpag.agents.rljax_agents.algorithm.sac_discor module xpag.agents.rljax_agents.algorithm.td3 module xpag.agents.rljax_agents.algorithm.tqc module xpag.agents.rljax_agents.network module xpag.agents.rljax_agents.network.actor module xpag.agents.rljax_agents.network.base module xpag.agents.rljax_agents.network.critic module xpag.agents.rljax_agents.network.initializer module xpag.agents.rljax_agents.rljax_interface module

xpag.agents.rljax_agents.util module xpag.agents.rljax_agents.util.distribution module xpag.agents.rljax_agents.util.input module xpag.agents.rljax_agents.util.loss module xpag.agents.rljax_agents.util.optim module xpag.agents.rljax_agents.util.preprocess module xpag.agents.rljax_agents.util.saving module xpag.buffers module xpag.buffers.buffer module xpag.buffers.jax_buffer module xpag.buffers.rljax_buffer module xpag.plotting module xpag.plotting.plotting module xpag.samplers module xpag.samplers.HER module xpag.samplers.jax_sampler module xpag.samplers.sampler module xpag.setters module xpag.setters.setter module xpag.tools module xpag.tools.eval module xpag.tools.learn module xpag.tools.logging module xpag.tools.replay module xpag.tools.timing module xpag.tools.utils module xpag.wrappers module xpag.wrappers.brax_vec_env module xpag.wrappers.goalenv_wrapper module xpag.wrappers.gym_vec_env module xpag.wrappers.reset_done module