Index

A

a (Tau attribute) abs_path() (in module alf.utils.common) absorbed() (PPGTrainInfo method) AbsTransform (in module alf.utils.dist_utils) ac (TracInfo attribute) accumulate_algorithm_rewards() (AgentHelper static method) accumulate_loss_info() (AgentHelper method) act() (Player method) (VehicleController method) action (ActionRepeatState attribute) (ActorCriticInfo attribute) (BasicRLInfo attribute) (DdpgInfo attribute) (IqlInfo attribute) (IqlState attribute) (MdqInfo attribute) (ModelTarget attribute) (MuzeroInfo attribute) (PPGRolloutInfo attribute) (PPOInfo attribute) (PredictiveRepresentationLearnerInfo attribute) (SacInfo attribute) (SacState attribute) action() (ContinuousActionClip method) (ContinuousActionMapping method) (LimitedDiscreteActions method) action_bins (ActionQuantizer property) action_desc() (CarlaEnvironment method) (Player method) (VehicleController method) action_discretize() (in module alf.environments.suite_dmlab) action_distribution (ActorCriticInfo attribute) (DdpgInfo attribute) (IqlInfo attribute) (ModelOutput attribute) (PPGRolloutInfo attribute) (PPOInfo attribute) (SacInfo attribute) (SarsaInfo attribute) (TaacInfo attribute) (TracInfo attribute) action_importance_ratio() (in module alf.utils.value_ops) action_param (TracExperience attribute) action_policy (ModelTarget attribute) action_probs (ModelOutput attribute) action_sampler_state (MCTSState attribute) action_space (DMCGYMWrapper property) action_spec (ProcessEnvironment attribute) (RLAlgorithm property) action_spec() (AlfEnvironment method) (AlfEnvironmentBaseWrapper method) (AlfGym3Wrapper method) (AlfGymWrapper method) (AlfMetaDriveWrapper method) (BatchEnvironmentWrapper method) (CarlaEnvironment method) (CurriculumWrapper method) (DiscreteActionWrapper method) (FastParallelEnvironment method) (GoEnvironment method) (MultitaskWrapper method) (NormalizedActionWrapper method) (ParallelAlfEnvironment method) (Player method) (ProcessEnvironment method) (RandomAlfEnvironment method) (ThreadEnvironment method) (TicTacToeEnvironment method) (UnittestEnv method) (VehicleController method) action_to_ind() (ActionQuantizer method) ActionObservationWrapper (class in alf.environments.alf_wrappers) ActionQuantizer (class in alf.utils.action_quantizer) ActionRepeatState (class in alf.algorithms.dynamic_action_repeat_agent) actions (ModelOutput attribute) ActionScalarization (class in alf.environments.suite_highway) ActionType (class in alf.algorithms.sac_algorithm) (class in alf.environments.suite_unittest) activate_ddp() (Algorithm method) active_action_target_entropy() (in module alf.utils.common) actor (ActorCriticState attribute) (BcInfo attribute), [1] (BcState attribute), [1] (DdpgActorState attribute) (DdpgLossInfo attribute) (DdpgState attribute) (IqlInfo attribute) (IqlLossInfo attribute) (IqlState attribute) (SacInfo attribute) (SacLossInfo attribute) (SacState attribute) (SarsaLossInfo attribute) (SarsaState attribute) (TaacInfo attribute) (TaacLossInfo attribute) actor_a (ActPredOutput attribute) actor_loss (DdpgInfo attribute) (IqlActorInfo attribute) (SacActorInfo attribute) (SarsaInfo attribute) (TaacActorInfo attribute) actor_network (IqlActionState attribute) (SacActionState attribute) ActorCriticAlgorithm (class in alf.algorithms.actor_critic_algorithm) ActorCriticInfo (class in alf.algorithms.actor_critic_algorithm) ActorCriticLoss (class in alf.algorithms.actor_critic_loss) ActorCriticLossInfo (class in alf.algorithms.actor_critic_loss) ActorCriticState (class in alf.algorithms.actor_critic_algorithm) ActorDistributionNetwork (class in alf.networks.actor_distribution_networks) ActorDistributionNetworkBase (class in alf.networks.actor_distribution_networks) ActorDistributionRNNNetwork (class in alf.networks.actor_distribution_networks) ActorNetwork (class in alf.networks.actor_networks) ActorNetworkBase (class in alf.networks.actor_networks) ActorRNNNetwork (class in alf.networks.actor_networks) ActPredOutput (class in alf.algorithms.taac_algorithm) Adam (in module alf.optimizers.optimizers) AdamTF (class in alf.optimizers.adam_tf) (in module alf.optimizers.optimizers) AdamW (class in alf.optimizers.adamw) (in module alf.optimizers.optimizers) AdaptiveAverager (class in alf.utils.averager) AdaptiveNormalizer (class in alf.utils.normalizers) add_actor() (World method) add_batch() (DataBuffer method) (ReplayBuffer method) add_batch_info() (in module alf.data_structures) add_ignore_empty() (in module alf.utils.math_ops) add_mean_hist_summary() (in module alf.utils.summary_utils) add_mean_summary() (in module alf.utils.summary_utils) add_method() (in module alf.utils.common) add_n() (in module alf.utils.math_ops) add_nested_summaries() (in module alf.utils.summary_utils) add_optimizer() (Algorithm method) add_param_group() (NeroPlus method) AddN (class in alf.layers) adjust_alpha() (EntropyTargetAlgorithm method) adjust_replay_buffer_length() (in module alf.algorithms.rl_algorithm) adjust_step() (TrustedUpdater method) adjust_weather_parameters() (in module alf.environments.suite_carla) adv (TaacActorInfo attribute) advantages (PPOInfo attribute) AffineTransform (class in alf.utils.dist_utils) AffineTransformedDistribution (class in alf.utils.dist_utils) after_train_iter() (Agent method) (AgentHelper method) (AlgorithmContainer method) (AlgorithmInterface method) (EchoAlg method) (LagrangianRewardWeightAlgorithm method) (MuzeroRepresentationLearner method) (PPGAlgorithm method) (RLAlgWrapper method) after_update() (Agent method) (AgentHelper method) (AlgorithmContainer method) (AlgorithmInterface method) (DdpgAlgorithm method) (DynamicActionRepeatAgent method) (EchoAlg method) (Generator method) (IqlAlgorithm method) (MbrlAlgorithm method) (MdqAlgorithm method) (MuzeroAlgorithm method) (MuzeroRepresentationImpl method) (MuzeroRepresentationLearner method) (RandomShootingAlgorithm method) (RLAlgWrapper method) (SacAlgorithm method) (SarsaAlgorithm method) (TaacAlgorithmBase method) (TracAlgorithm method) Agent (class in alf.algorithms.agent) AgentHelper (class in alf.algorithms.agent_helpers) AgentInfo (class in alf.algorithms.agent) AgentPerception (class in alf.environments.metadrive.agent_perception) AgentState (class in alf.algorithms.agent) alf module alf.algorithms module alf.algorithms.actor_critic_algorithm module alf.algorithms.actor_critic_loss module alf.algorithms.agent module alf.algorithms.agent_helpers module alf.algorithms.algorithm module alf.algorithms.algorithm_interface module alf.algorithms.async_unroller module alf.algorithms.bc_algorithm module alf.algorithms.causal_bc_algorithm module alf.algorithms.config module alf.algorithms.containers module alf.algorithms.data_transformer module alf.algorithms.ddpg_algorithm module alf.algorithms.decoding_algorithm module alf.algorithms.diayn_algorithm module alf.algorithms.dqn_algorithm module alf.algorithms.dynamic_action_repeat_agent module alf.algorithms.dynamics_learning_algorithm module alf.algorithms.encoding_algorithm module alf.algorithms.entropy_target_algorithm module alf.algorithms.functional_particle_vi_algorithm module alf.algorithms.generator module alf.algorithms.goal_generator module alf.algorithms.handcrafted_algorithm module alf.algorithms.hypernetwork_algorithm module alf.algorithms.icm_algorithm module alf.algorithms.iql_algorithm module alf.algorithms.lagrangian_reward_weight_algorithm module alf.algorithms.mbrl_algorithm module alf.algorithms.mcts_algorithm module alf.algorithms.mcts_models module alf.algorithms.mdq_algorithm module alf.algorithms.merlin_algorithm module alf.algorithms.mi_estimator module alf.algorithms.monet_algorithm module alf.algorithms.muzero_algorithm module alf.algorithms.muzero_representation_learner module alf.algorithms.oac_algorithm module alf.algorithms.off_policy_algorithm module alf.algorithms.on_policy_algorithm module alf.algorithms.one_step_loss module alf.algorithms.particle_vi_algorithm module alf.algorithms.planning_algorithm module alf.algorithms.ppg module alf.algorithms.ppg.disjoint_policy_value_network module alf.algorithms.ppg.ppg_aux_algorithm module alf.algorithms.ppg.ppg_aux_phase_loss module alf.algorithms.ppg.ppg_utils module alf.algorithms.ppg_algorithm module alf.algorithms.ppo_algorithm module alf.algorithms.ppo_loss module alf.algorithms.predictive_representation_learner module alf.algorithms.prior_actor module alf.algorithms.qrsac_algorithm module alf.algorithms.reward_learning_algorithm module alf.algorithms.rl_algorithm module alf.algorithms.rnd_algorithm module alf.algorithms.sac_algorithm module alf.algorithms.sarsa_algorithm module alf.algorithms.taac_algorithm module alf.algorithms.td_loss module alf.algorithms.trac_algorithm module alf.algorithms.vae module alf.algorithms.vq_vae module alf.bin module alf.bin.compare module alf.bin.grid_search module alf.bin.play module alf.bin.train module

alf.bin.verify_checkpoint module alf.config_helpers module alf.config_util module alf.data_structures module alf.device_ctx module alf.environments module alf.environments.adv_fetch_envs module alf.environments.alf_environment module alf.environments.alf_gym3_wrapper module alf.environments.alf_gym_wrapper module alf.environments.alf_wrappers module alf.environments.carla_controller module alf.environments.carla_sensors module alf.environments.carla_spectator module alf.environments.dmc_gym_wrapper module alf.environments.fast_parallel_environment module alf.environments.gym_wrappers module alf.environments.make_penv module alf.environments.mario_wrappers module alf.environments.metadrive module alf.environments.metadrive.agent_perception module alf.environments.metadrive.environments module alf.environments.metadrive.extra_rewards module alf.environments.metadrive.geometry module alf.environments.metadrive.map_perception module alf.environments.metadrive.renderer module alf.environments.metadrive.sensors module alf.environments.parallel_environment module alf.environments.process_environment module alf.environments.random_alf_environment module alf.environments.simple module alf.environments.simple.noisy_array module alf.environments.simple.stochastic_with_risky_branch module alf.environments.suite_babyai module alf.environments.suite_bsuite module alf.environments.suite_carla module alf.environments.suite_dmc module alf.environments.suite_dmlab module alf.environments.suite_go module alf.environments.suite_gym module alf.environments.suite_highway module alf.environments.suite_mario module alf.environments.suite_metadrive module alf.environments.suite_procgen module alf.environments.suite_simple module alf.environments.suite_socialbot module alf.environments.suite_tic_tac_toe module alf.environments.suite_unittest module alf.environments.thread_environment module alf.environments.utils module alf.experience_replayers module alf.experience_replayers.replay_buffer module alf.experience_replayers.segment_tree module alf.initializers module alf.layers module alf.metrics module alf.metrics.metric module alf.metrics.metrics module alf.module module alf.nest module alf.nest.nest module alf.nest.utils module alf.networks module alf.networks.action_encoder module alf.networks.actor_distribution_networks module alf.networks.actor_networks module alf.networks.containers module alf.networks.critic_networks module alf.networks.dynamics_networks module alf.networks.encoding_networks module alf.networks.mdq_critic_networks module alf.networks.memory module alf.networks.network module alf.networks.networks module alf.networks.normalizing_flow_networks module alf.networks.ou_process module alf.networks.param_networks module alf.networks.preprocessor_networks module alf.networks.preprocessors module alf.networks.projection_networks module alf.networks.q_networks module alf.networks.relu_mlp module alf.networks.transformer_networks module alf.networks.value_networks module alf.norm_layers module alf.optimizers module alf.optimizers.adam_tf module alf.optimizers.adamw module alf.optimizers.nero_plus module alf.optimizers.optimizers module alf.optimizers.traj_optimizers module alf.optimizers.trusted_updater module alf.optimizers.utils module alf.summary module alf.summary.render module alf.summary.summary_ops module alf.tensor_specs module alf.test module alf.test.case module alf.test.main module alf.trainers module alf.trainers.evaluator module alf.trainers.policy_trainer module alf.utils module alf.utils.action_quantizer module alf.utils.action_samplers module alf.utils.averager module alf.utils.checkpoint_utils module alf.utils.common module alf.utils.conditional_ops module alf.utils.data_buffer module alf.utils.datagen module alf.utils.dist_utils module alf.utils.distributed module alf.utils.distributions module alf.utils.external_configurables module alf.utils.gin_utils module alf.utils.git_utils module alf.utils.lean_function module alf.utils.losses module alf.utils.math_ops module alf.utils.normalizers module alf.utils.per_process_context module alf.utils.plot_tb_curves module alf.utils.pretty_print module alf.utils.process_coordinator module alf.utils.schedulers module alf.utils.sl_utils module alf.utils.spec_utils module alf.utils.summary_utils module alf.utils.tensor_utils module alf.utils.value_ops module alf.utils.video_recorder module alf.utils.visualizer module alf_root() (in module alf.utils.common) AlfEnvironment (class in alf.environments.alf_environment) AlfEnvironmentBaseWrapper (class in alf.environments.alf_wrappers) AlfGym3Wrapper (class in alf.environments.alf_gym3_wrapper) AlfGymWrapper (class in alf.environments.alf_gym_wrapper) AlfMetaDriveWrapper (class in alf.environments.suite_metadrive) Algorithm (class in alf.algorithms.algorithm) AlgorithmContainer (class in alf.algorithms.containers) AlgorithmInterface (class in alf.algorithms.algorithm_interface) AlgStep (class in alf.data_structures) alpha (MdqInfo attribute) (MdqLossInfo attribute) (SacInfo attribute) (SacLossInfo attribute) (SarsaLossInfo attribute) (TaacInfo attribute) (TaacLossInfo attribute) alpha_loss (MdqAlphaInfo attribute) AMPWrapper (class in alf.layers) (class in alf.networks.networks) append() (MetricBuffer method) append_coordinate() (in module alf.utils.tensor_utils) arg_constraints (TruncatedDistribution attribute) argmin() (in module alf.utils.math_ops) as_list() (in module alf.utils.common) as_scheduler() (in module alf.utils.schedulers) assert_same_length() (in module alf.nest.nest) assert_same_structure() (in module alf.nest.nest) assert_same_structure_up_to() (in module alf.nest.nest) assert_same_type() (in module alf.nest.nest) assertArrayClose() (TestCase method) assertArrayEqual() (TestCase method) assertArrayNotClose() (TestCase method) assertTensorClose() (TestCase method) assertTensorEqual() (TestCase method) assertTensorNotClose() (TestCase method) AsymmetricSimSiamLoss (class in alf.utils.losses) AsyncUnroller (class in alf.algorithms.async_unroller) AtariTerminalOnLifeLossWrapper (class in alf.environments.alf_wrappers) atomic() (in module alf.utils.data_buffer) auc_score() (in module alf.utils.sl_utils) AutoShapeImageDeconvNetwork (class in alf.networks.encoding_networks) aux (PPGRolloutInfo attribute) average() (EMAverager method) (WindowAverager method) average_outer_dims() (in module alf.utils.averager) AverageDiscountedReturnMetric (class in alf.metrics.metrics) AverageEnvInfoMetric (class in alf.metrics.metrics) AverageEpisodeLengthMetric (class in alf.metrics.metrics) AverageEpisodicAggregationMetric (class in alf.metrics.metrics) AverageReturnMetric (class in alf.metrics.metrics) AverageRewardMetric (class in alf.metrics.metrics)

B

b (ActPredOutput attribute) (TaacInfo attribute) b1_a_dist (Distributions attribute) b1_a_entropy (TaacActorInfo attribute) BabyAIWrapper (class in alf.environments.suite_babyai) backward() (Softsign static method) (Softsign_ static method) (T2Cdf_ static method) BaseObservationWrapper (class in alf.environments.gym_wrappers) BasicRLInfo (class in alf.data_structures) BasicRolloutInfo (class in alf.data_structures) batch_label (LossInfo attribute) batch_nested_tensor() (in module alf.nest.nest) batch_size (AlfEnvironment property) (AlfEnvironmentBaseWrapper property) (AlfGym3Wrapper property) (BatchEnvironmentWrapper property) (CarlaEnvironment property) (FastParallelEnvironment property) (GoEnvironment property) (ParallelAlfEnvironment property) (RandomAlfEnvironment property) (ThreadEnvironment property) (TicTacToeEnvironment property) (UnittestEnv property) batched (AlfEnvironment property) (AlfEnvironmentBaseWrapper property) (AlfGym3Wrapper property) (AlfMetaDriveWrapper property) (BatchEnvironmentWrapper property) (CarlaEnvironment property) (FastParallelEnvironment property) (GoEnvironment property) (ParallelAlfEnvironment property) (Polyline property) (RandomAlfEnvironment property) (ThreadEnvironment property) (TicTacToeEnvironment property) (UnittestEnv property) BatchedTensorWrapper (class in alf.environments.alf_wrappers) BatchEnvironmentWrapper (class in alf.environments.alf_wrappers) BatchInfo (class in alf.experience_replayers.replay_buffer) BatchNorm1d (class in alf.norm_layers) BatchNorm2d (class in alf.norm_layers) BatchSquash (class in alf.utils.tensor_utils) BatchSquashNetwork (class in alf.networks.network) bbox (FieldOfView property)

BcAlgorithm (class in alf.algorithms.bc_algorithm) BcInfo (class in alf.algorithms.bc_algorithm) (class in alf.algorithms.causal_bc_algorithm) BcLossInfo (in module alf.algorithms.bc_algorithm) (in module alf.algorithms.causal_bc_algorithm) BcState (class in alf.algorithms.bc_algorithm) (class in alf.algorithms.causal_bc_algorithm) Beta (class in alf.utils.dist_utils) beta (VAEInfo attribute) beta_dist (Distributions attribute) beta_entropy (TaacActorInfo attribute) beta_loss (VAEInfo attribute) BetaProjectionNetwork (class in alf.networks.projection_networks) BEVSensor (class in alf.environments.carla_sensors) beyond_episode_end (ModelTarget attribute) bias (CausalConv1D property) (CompositionalFC property) (Conv2D property) (ConvTranspose2D property) (FC property) (NoisyFC property) (ParallelConv2D property) (ParallelConvTranspose2D property) (ParallelFC property) (ParamConv2D property) (ParamFC property) (ParamLayerNorm property) bias_length (ParamConv2D property) (ParamFC property) (ParamLayerNorm property) bijective (Softclip attribute) (Softplus attribute) (Softsign attribute) (StableTanh attribute) binary_neg_entropy() (in module alf.utils.math_ops) BipartiteMatchingLoss (class in alf.utils.losses) BirdEyeObservation (class in alf.environments.metadrive.sensors) BirdEyeTopDownEnv (class in alf.environments.metadrive.environments) body() (Process method) BottleneckBlock (class in alf.layers) BoundedTensorSpec (class in alf.tensor_specs) Branch (class in alf.layers) Branch() (in module alf.networks.containers) BSuiteWrapper (class in alf.environments.suite_bsuite) build() (FIFOMemory method) (MemoryWithUsage method) build_distribution() (DistributionSpec method) BUTTONS (LimitedDiscreteActions attribute)

C

cache_frame_and_pred_info() (VideoRecorder method) calc_area() (GoBoard method) calc_area_simple() (GoBoard method) calc_default_max_entropy() (in module alf.utils.dist_utils) calc_default_target_entropy() (in module alf.utils.dist_utils) calc_default_target_entropy_quantized() (in module alf.utils.dist_utils) calc_expectation() (DiscreteRegressionLoss method) (OrderedDiscreteRegressionLoss method) (QuantileRegressionLoss method) (ScalarPredictionLoss method) (SquareLoss method) calc_loss() (ActorCriticAlgorithm method) (ActorCriticLoss method) (Agent method) (Algorithm method) (AlgorithmContainer method) (AlgorithmInterface method) (DdpgAlgorithm method) (DIAYNAlgorithm method) (DqnAlgorithm method) (DynamicActionRepeatAgent method) (DynamicsLearningAlgorithm method) (EchoAlg method) (EntropyTargetAlgorithm method) (HandcraftedAlgorithm method) (ICMAlgorithm method) (IqlAlgorithm method) (LatentMbrlAlgorithm method) (Loss method) (MbrlAlgorithm method) (MCTSModel method) (MdqAlgorithm method) (MemoryBasedActor method) (MerlinAlgorithm method) (MoNetAlgorithm method) (MuzeroAlgorithm method) (MuzeroRepresentationImpl method) (MuzeroRepresentationLearner method) (NestedEntropyTargetAlgorithm method) (PPGAlgorithm method) (PPGAuxAlgorithm method) (RandomCategoricalGoalGenerator method) (RLAlgWrapper method) (RNDAlgorithm method) (SacAlgorithm method) (SarsaAlgorithm method) (SGDEntropyTargetAlgorithm method) (SimpleDecoder method) (TaacAlgorithmBase method) (TracAlgorithm method) calc_loss_offline() (Agent method) (Algorithm method) (AlgorithmInterface method) (BcAlgorithm method) (CausalBcAlgorithm method) calc_output_shape() (BottleneckBlock method) calc_pmi() (MIEstimator method) calc_repr_prediction_loss() (MCTSModel method) calc_uniform_log_prob() (in module alf.utils.dist_utils) calculate_exploration_policy() (in module alf.algorithms.mcts_algorithm) calculate_kl_exploration_policy() (in module alf.algorithms.mcts_algorithm) call() (AverageEpisodicAggregationMetric method) (EnvironmentSteps method) (NumberOfEpisodes method) (ProcessEnvironment method) (StepMetric method) call_stack() (in module alf.utils.common) CameraSensor (class in alf.environments.carla_sensors) candidate_action_policy (MCTSInfo attribute) candidate_actions (MCTSInfo attribute) capture_env_frame() (VideoRecorder method) capture_frame() (VideoRecorder method) CarlaEnvironment (class in alf.environments.suite_carla) CarlaServer (class in alf.environments.suite_carla) Cast (class in alf.layers) cast_transformer() (in module alf.utils.common) CategoricalProjectionNetwork (class in alf.networks.projection_networks) CategoricalSeedSampler (class in alf.utils.action_samplers) category (Polyline attribute) CategoryEncoder (class in alf.environments.metadrive.geometry) CauchyITS (class in alf.utils.distributions) CauchyProjectionNetwork (class in alf.networks.projection_networks) CausalBcAlgorithm (class in alf.algorithms.causal_bc_algorithm) CausalConv1D (class in alf.layers) cdf() (CauchyITS static method) (InverseTransformSampling static method) (NormalITS static method) (T2ITS static method) CEMOptimizer (class in alf.optimizers.traj_optimizers) CEMPlanAlgorithm (class in alf.algorithms.planning_algorithm) check() (UnwrappedEnvChecker method) check_and_update() (UnwrappedEnvChecker method) check_convert_env_ids() (RingBuffer method) check_numerics() (in module alf.utils.common) Checkpointer (class in alf.utils.checkpoint_utils) circular() (RingBuffer method) classification_loss() (in module alf.utils.sl_utils) classify_all_moves() (GoBoard method) clean() (DynamicObjectSensor method) clear() (MetricBuffer method) (RingBuffer method) clear_batch_info() (in module alf.data_structures) clear_cache() (VideoRecorder method) clear_stop() (Coordinator method) clip_by_global_norm() (in module alf.utils.tensor_utils) clip_by_norms() (in module alf.utils.tensor_utils) clip_to_spec() (in module alf.utils.spec_utils) clip_value (RewardNormalizer property) clipped_exp() (in module alf.utils.math_ops) close() (AlfEnvironment method) (AlfEnvironmentBaseWrapper method) (AlfGymWrapper method) (AlfMetaDriveWrapper method) (AsyncUnroller method) (BatchEnvironmentWrapper method) (CarlaEnvironment method) (DeepmindLabEnv method) (Evaluator method) (FastParallelEnvironment method) (ParallelAlfEnvironment method) (ProcessEnvironment method) (ThreadEnvironment method)

close_env() (in module alf.config_helpers) codomain (Softclip attribute) (Softplus attribute) (Softsign attribute) (StableTanh attribute) CollisionSensor (class in alf.environments.carla_sensors) color (NumpyLaneMarking attribute) commitment (VqvaeLossInfo attribute) CompositionalFC (class in alf.layers) compute_entropy() (in module alf.utils.dist_utils) compute_jac() (ReluMLP method) compute_jac_diag() (ReluMLP method) compute_jvp() (ReluMLP method) compute_log_probability() (in module alf.utils.dist_utils) compute_paras_statistics() (Algorithm method) compute_reward() (FixedRewardFunction method) (RewardEstimationAlgorithm method) compute_summary_or_eval_interval() (in module alf.utils.common) compute_td_target() (TDLoss method) compute_vjp() (ReluMLP method) concentration0 (Beta property) concentration1 (Beta property) conditional_update() (in module alf.utils.conditional_ops) config() (in module alf.config_util) config1() (in module alf.config_util) configurable() (in module alf.config_util) constant() (TensorSpec method) ConstantScheduler (class in alf.utils.schedulers) Continuous (ActionType attribute), [1] ContinuousActionClip (class in alf.environments.gym_wrappers) ContinuousActionMapping (class in alf.environments.gym_wrappers) Conv2D (class in alf.layers) Conv2DBatchEnsemble (class in alf.layers) convert_device() (in module alf.nest.utils) convert_train_state_to_predict_state() (ActorCriticAlgorithm method) (Algorithm method) (SarsaAlgorithm method) ConvTranspose2D (class in alf.layers) Coordinator (class in alf.utils.process_coordinator) copy() (Network method) copy_gin_configs() (in module alf.utils.common) cov() (in module alf.utils.tensor_utils) cpu() (TimeStep method) CrashVehicleReward (class in alf.environments.metadrive.extra_rewards) create_atari_mcts() (in module alf.algorithms.mcts_algorithm) create_board_game_mcts() (in module alf.algorithms.mcts_algorithm) create_chess_mcts() (in module alf.algorithms.mcts_algorithm) create_control_mcts() (in module alf.algorithms.mcts_algorithm) create_data_transformer() (in module alf.algorithms.data_transformer) create_discrete_skill_spec() (in module alf.algorithms.diayn_algorithm) create_environment() (in module alf.environments.utils) create_go_mcts() (in module alf.algorithms.mcts_algorithm) create_keynet() (MemoryWithUsage method) create_ou_process() (in module alf.utils.common) create_shogi_mcts() (in module alf.algorithms.mcts_algorithm) create_simple_dynamics_net() (in module alf.algorithms.mcts_models) create_simple_encoding_net() (in module alf.algorithms.mcts_models) create_simple_prediction_net() (in module alf.algorithms.mcts_models) create_summary_writer() (in module alf.summary.summary_ops) critic (DdpgInfo attribute) (DdpgLossInfo attribute) (IqlActionState attribute) (IqlInfo attribute) (IqlLossInfo attribute) (IqlState attribute) (MdqCriticState attribute) (MdqInfo attribute) (MdqLossInfo attribute) (MdqState attribute) (SacActionState attribute) (SacInfo attribute) (SacLossInfo attribute) (SacState attribute) (SarsaLossInfo attribute) (TaacInfo attribute) (TaacLossInfo attribute) critic_adv_form (MdqCriticInfo attribute) critic_free_form (MdqCriticInfo attribute) critic_network_visualizer() (in module alf.utils.visualizer) CriticAlgorithm (class in alf.algorithms.generator) CriticNetwork (class in alf.networks.critic_networks) CriticRNNNetwork (class in alf.networks.critic_networks) critics (DdpgActorState attribute) (DdpgCriticState attribute) (DdpgState attribute) (IqlCriticInfo attribute) (IqlCriticState attribute) (SacCriticInfo attribute) (SacCriticState attribute) (SarsaInfo attribute) (SarsaState attribute) (TaacCriticInfo attribute) cuda() (TimeStep method) current_env_steps() (Trainer static method) current_iterations() (Trainer static method) current_pos (DataBuffer property) current_size (DataBuffer property) current_time_step() (AlfEnvironment method) CurriculumWrapper (class in alf.environments.alf_wrappers) CurvesPlotter (class in alf.utils.plot_tb_curves) CyclicalScheduler (class in alf.utils.schedulers)

D

data (Image property) data_distributed() (in module alf.utils.distributed) data_distributed_when() (in module alf.utils.distributed) DataBuffer (class in alf.utils.data_buffer) DataTransformer (class in alf.algorithms.data_transformer) ddp_rank (PerProcessContext property) DdpgActorState (class in alf.algorithms.ddpg_algorithm) DdpgAlgorithm (class in alf.algorithms.ddpg_algorithm) DdpgCriticInfo (class in alf.algorithms.ddpg_algorithm) DdpgCriticState (class in alf.algorithms.ddpg_algorithm) DdpgInfo (class in alf.algorithms.ddpg_algorithm) DdpgLossInfo (class in alf.algorithms.ddpg_algorithm) DdpgState (class in alf.algorithms.ddpg_algorithm) decode_step() (MemoryBasedPredictor method) decoder (MBPLossInfo attribute) DecodingAlgorithm (class in alf.algorithms.decoding_algorithm) DeepmindLabEnv (class in alf.environments.suite_dmlab) default_config() (BirdEyeTopDownEnv class method) (VectorizedTopDownEnv class method) DEFAULT_ENCOUNTERED_RED_LIGHT_DISTANCE (World attribute) default_optimizer (Algorithm property) define_config() (in module alf.config_util) Delay (class in alf.networks.networks) dequeue() (ReplayBuffer method) (RingBuffer method) desc (GridSearchConfig property) destroy() (DynamicObjectSensor method) (Player method) (SensorBase method) Detach (class in alf.layers) detach() (in module alf.utils.common) DeterministicDynamicsAlgorithm (class in alf.algorithms.dynamics_learning_algorithm) device (class in alf.device_ctx) (RingBuffer property) DiagMultivariateBeta (class in alf.utils.dist_utils) DiagMultivariateCauchy (class in alf.utils.dist_utils) DiagMultivariateNormal (class in alf.utils.dist_utils) DIAYNAlgorithm (class in alf.algorithms.diayn_algorithm) DIAYNInfo (class in alf.algorithms.diayn_algorithm) dim (Memory property) disable_summary() (in module alf.summary.summary_ops) discount (ActorCriticInfo attribute) (DdpgInfo attribute) (Experience property) (IqlInfo attribute) (MCTSAlgorithm property) (MdqInfo attribute) (PPGRolloutInfo attribute) (PPOInfo attribute) (SacInfo attribute) (SarsaInfo attribute) (TaacInfo attribute)

discounted_return (BatchInfo attribute) (DdpgInfo attribute) (SacInfo attribute) discounted_return() (in module alf.utils.value_ops) Discrete (ActionType attribute), [1] DiscreteActionWrapper (class in alf.environments.alf_wrappers) DiscreteRegressionLoss (class in alf.utils.losses) DiscreteVAE (class in alf.algorithms.vae) discriminator (BcInfo attribute) DisjointPolicyValueNetwork (class in alf.algorithms.ppg.disjoint_policy_value_network) dist (DynamicsInfo attribute) distill (MdqLossInfo attribute) distill_target (MdqCriticInfo attribute) Distributions (class in alf.algorithms.taac_algorithm) distributions_to_params() (in module alf.utils.dist_utils) DistributionSpec (class in alf.utils.dist_utils) dists (ActPredOutput attribute) DMAtariPreprocessing (class in alf.environments.gym_wrappers) DMCGYMWrapper (class in alf.environments.dmc_gym_wrapper) domain (Softclip attribute) (Softplus attribute) (Softsign attribute) (StableTanh attribute) done (AlfGymWrapper property) DqnAlgorithm (class in alf.algorithms.dqn_algorithm) dtype (TensorSpec property) dtype_str (TensorSpec property) duration (PerformanceProfiler property) (TimeLimit property) DynamicActionRepeatAgent (class in alf.algorithms.dynamic_action_repeat_agent) DynamicObjectSensor (class in alf.environments.carla_sensors) dynamics (MbrlInfo attribute) (MbrlState attribute) DynamicsInfo (class in alf.algorithms.dynamics_learning_algorithm) DynamicsLearningAlgorithm (class in alf.algorithms.dynamics_learning_algorithm) DynamicsNetwork (class in alf.networks.dynamics_networks) DynamicsState (class in alf.algorithms.dynamics_learning_algorithm)

E

Echo (class in alf.networks.containers) EchoAlg (class in alf.algorithms.containers) EgoKinematicReward (class in alf.environments.metadrive.extra_rewards) elastic_namedtuple() (in module alf.data_structures) element_wise_huber_loss() (in module alf.utils.losses) element_wise_squared_loss() (in module alf.utils.losses) ElementwiseLayerBase (class in alf.layers) ema_smooth() (in module alf.utils.plot_tb_curves) EMAverager (class in alf.utils.averager) embedding() (in module alf.summary.summary_ops) EmbeddingPreprocessor (class in alf.networks.preprocessors) EMNormalizer (class in alf.utils.normalizers) enable_checkpoint() (in module alf.utils.checkpoint_utils) enable_rendering() (in module alf.summary.render) enable_summary() (in module alf.summary.summary_ops) enabled (PPGAuxOptions attribute) encode_line_type() (CategoryEncoder method) encode_navigation() (CategoryEncoder method) encode_step() (MemoryBasedPredictor method) EncodingAlgorithm (class in alf.algorithms.encoding_algorithm) EncodingNetwork (class in alf.networks.encoding_networks) enqueue() (RingBuffer method) EnsureSummary (class in alf.summary.summary_ops) enter_summary_scope() (in module alf.summary.summary_ops) entropy() (AffineTransformedDistribution method) entropy_target (AgentInfo attribute) entropy_with_fallback() (in module alf.utils.dist_utils) EntropyTargetAlgorithm (class in alf.algorithms.entropy_target_algorithm) EntropyTargetInfo (class in alf.algorithms.entropy_target_algorithm) EntropyTargetLossInfo (class in alf.algorithms.entropy_target_algorithm) env_id (Experience property) env_ids (BatchInfo attribute) env_info_spec() (AlfEnvironment method) (AlfEnvironmentBaseWrapper method) (AlfGym3Wrapper method) (AlfGymWrapper method) (AlfMetaDriveWrapper method) (BatchEnvironmentWrapper method) (CarlaEnvironment method) (CrashVehicleReward method) (CurriculumWrapper method) (EgoKinematicReward method) (ExtraReward method) (FastParallelEnvironment method) (GoEnvironment method) (LaneKeepingReward method) (MultitaskWrapper method) (ParallelAlfEnvironment method) (ProcessEnvironment method) (RandomAlfEnvironment method) (ThreadEnvironment method) (TicTacToeEnvironment method) (UnittestEnv method)

env_step_time (UnrollResult attribute) EnvironmentSteps (class in alf.metrics.metrics) EnvironmentStepsReturnReader (class in alf.utils.plot_tb_curves) EnvironmentStepsSuccessReader (class in alf.utils.plot_tb_curves) envs (FastParallelEnvironment property) (ParallelAlfEnvironment property) EpisodicRandomFrameCrop (class in alf.environments.gym_wrappers) EpisodicStartAverageDiscountedReturnMetric (class in alf.metrics.metrics) epsilon_greedy_sample() (in module alf.utils.dist_utils) EpsilonGreedySampler (class in alf.utils.action_samplers) estimated_entropy() (in module alf.utils.dist_utils) eval() (Evaluator method) (SyncEvaluator method) eval_context (class in alf.utils.common) eval_uncertainty() (FuncParVIAlgorithm method) (HyperNetwork method) EvalJob (class in alf.trainers.evaluator) evaluate() (CrashVehicleReward method) (EgoKinematicReward method) (ExtraReward method) (FuncParVIAlgorithm method) (HyperNetwork method) (LaneKeepingReward method) Evaluator (class in alf.trainers.evaluator) exe_mode_name() (in module alf.utils.common) expand_dims_as() (in module alf.utils.common) Experience (class in alf.data_structures) experience_spec (Algorithm property) explained_variance() (in module alf.utils.tensor_utils) ExponentialScheduler (class in alf.utils.schedulers) ExpTransform (in module alf.utils.dist_utils) extra (LossInfo attribute) extract_any_leaf_from_nest() (in module alf.nest.nest) extract_distribution_parameters() (in module alf.utils.dist_utils) extract_fields_from_nest() (in module alf.nest.nest) extract_spec() (in module alf.utils.dist_utils) extract_sub_state_dict_from_checkpoint() (in module alf.utils.checkpoint_utils) extract_weather_parameters() (in module alf.environments.suite_carla) ExtraReward (class in alf.environments.metadrive.extra_rewards)

F

fast_map_structure() (in module alf.nest.nest) fast_map_structure_flatten() (in module alf.nest.nest) FastParallelEnvironment (class in alf.environments.fast_parallel_environment) FC (class in alf.layers) FCBatchEnsemble (class in alf.layers) feature (DynamicsState attribute) FieldOfView (class in alf.environments.metadrive.geometry) FIFOMemory (class in alf.networks.memory) final_y() (MeanCurve method) finalize() (PerProcessContext method) find_field() (in module alf.nest.nest) find_sum_bound() (SumSegmentTree method) finish_train() (RLAlgorithm method) FIRE (NoisyArray attribute) fire() (DMAtariPreprocessing method) FIRST (StepType attribute) FixedDecodingLayer (class in alf.layers) FixedRewardFunction (class in alf.algorithms.reward_learning_algorithm) flatten() (BatchSquash method) (in module alf.nest.nest) flatten_up_to() (in module alf.nest.nest) flattened_size() (in module alf.utils.common) FlattenObservation (class in alf.environments.suite_highway) force_params_visible_to_parent (Algorithm property) format_namedtuple() (PrettyPrinter method) format_namedtuple_items() (PrettyPrinter method) forward() (ActorCriticLoss method) (ActorDistributionNetworkBase method) (ActorNetworkBase method) (AddN method) (Algorithm method) (AMPWrapper method), [1] (AsymmetricSimSiamLoss method) (BatchSquashNetwork method) (BetaProjectionNetwork method) (BipartiteMatchingLoss method) (BottleneckBlock method) (Branch method) (Cast method) (CategoricalProjectionNetwork method) (CategoricalSeedSampler method) (CauchyProjectionNetwork method) (CausalConv1D method) (CompositionalFC method) (Conv2D method) (Conv2DBatchEnsemble method) (ConvTranspose2D method) (Delay method) (Detach method) (DisjointPolicyValueNetwork method) (DynamicsNetwork method) (Echo method) (EmbeddingPreprocessor method) (EpsilonGreedySampler method) (FC method) (FCBatchEnsemble method) (FixedDecodingLayer method) (FunctionalRewardTransformer method) (GetFields method) (GFT method) (GradientNoiseScaleEstimator method) (GRUCell method) (Identity method) (Lambda method) (LatentActorDistributionNetwork method) (LSTMCell method) (MdqCriticNetwork method) (MeanSquaredLoss method) (MixtureProjectionNetwork method) (MoNetUNet method) (MultinomialSampler method) (NaiveParallelLayer method) (NaiveParallelNetwork method) (NetworkWrapper method) (NoisyFC method) (Normalizer method) (NormalizingFlowNetwork method) (NormalProjectionNetwork method) (OneHot method) (OnehotCategoricalProjectionNetwork method) (OUProcess method), [1] (Parallel method) (ParallelActorDistributionNetwork method) (ParallelCategoricalProjectionNetwork method) (ParallelConv2D method) (ParallelConvTranspose2D method) (ParallelDynamicsNetwork method) (ParallelFC method) (ParallelQNetwork method) (ParallelValueNetwork method) (ParamConv2D method) (ParamConvNet method) (ParamFC method) (ParamLayerNorm method) (ParamNetwork method) (Periodically method) (Permute method) (PPGAuxPhaseLoss method) (PreprocessorNetwork method) (QNetworkBase method) (RandomCrop method) (ReluMLP method) (ReplicationPad2d method) (Reshape method) (Residue method) (ResidueBlock method) (ResnetDecodingNetwork method) (ResnetEncodingNetwork method) (RewardClipping method) (RewardNormalizer method) (RewardScaling method) (RewardShifting method) (Scale method) (ScaleGradient method) (SimpleActionEncoder method) (SimpleAttention method) (SimpleFC method) (SimplePredictionNet method) (SocialAttentionNetwork method) (Softsign static method) (Softsign_ static method) (StableNormalProjectionNetwork method) (StepMetric method) (Sum method) (SummarizeGradient method) (T2Cdf_ static method) (TAACTDLoss method) (TargetUpdater method) (TDLoss method) (TDQRLoss method) (TemporalPool method) (TransformerBlock method) (TransformerNetwork method) (Transpose method) (TruncatedProjectionNetwork method) (UnitNormalActorDistributionNetwork method) (ValueNetworkBase method)

forward_loss (ICMInfo attribute) FrameCrop (class in alf.environments.gym_wrappers) FrameFlip (class in alf.environments.gym_wrappers) FrameFormat (class in alf.environments.mario_wrappers) FrameGrayScale (class in alf.environments.gym_wrappers) FrameResize (class in alf.environments.gym_wrappers) FrameSkip (class in alf.environments.gym_wrappers) FrameStack (class in alf.environments.gym_wrappers) FrameStacker (class in alf.algorithms.data_transformer) FrameStackState (class in alf.algorithms.data_transformer) from_array() (TensorSpec class method) from_curves() (MeanCurve class method) from_distribution() (DistributionSpec class method) from_lane() (Polyline static method) from_pyplot_fig() (Image class method) from_spec() (BoundedTensorSpec class method) (TensorSpec class method) from_states() (FIFOMemory method) (MemoryWithUsage method) from_tensor() (TensorSpec class method) full_rec (MoNetInfo attribute) FuncParVIAlgorithm (class in alf.algorithms.functional_particle_vi_algorithm) FunctionalRewardTransformer (class in alf.algorithms.data_transformer)

G

game_over (ModelOutput attribute) (ModelTarget attribute) game_over_logit (ModelOutput attribute) gamma (ActorCriticLoss property) (TAACTDLoss property) (TDLoss property) gather_all() (ReplayBuffer method) gather_unroll_results() (AsyncUnroller method) gen_penv() (in module alf.environments.make_penv) gen_summaries() (StepMetric method) generalized_advantage_estimation() (in module alf.utils.value_ops) generate_alf_snapshot() (in module alf.utils.common) generate_observation_masks() (BEVSensor method) generate_video_from_cache() (VideoRecorder method) Generator (class in alf.algorithms.generator) generator (GeneratorLossInfo attribute) GeneratorLossInfo (class in alf.algorithms.generator) genkey_and_read() (MemoryWithUsage method) get() (EMAverager method) (WindowAverager method) get_action() (MdqCriticNetwork method) get_action_spec() (in module alf.config_helpers) (in module alf.utils.common) get_active_speed_limit() (World method) get_actor_location() (World method) get_actors() (World method) get_alf_snapshot_env_vars() (in module alf.utils.common) get_all() (DataBuffer method) get_all_config_names() (in module alf.config_util) get_all_parameters() (in module alf.utils.common) get_base_dist() (in module alf.utils.dist_utils) get_batch() (DataBuffer method) (ReplayBuffer method) get_batch_by_indices() (DataBuffer method) get_board() (GoBoard method) get_builder() (AffineTransform method) (Softclip method) get_classes() (in module alf.utils.datagen) get_codes() (CategoryEncoder method) get_conf_file() (in module alf.utils.common) get_config_value() (in module alf.config_util) get_current_observation() (BEVSensor method) (CameraSensor method) (CollisionSensor method) (DynamicObjectSensor method) (GnssSensor method) (IMUSensor method) (LaneInvasionSensor method) (NavigationSensor method) (ObstacleDetectionSensor method) (RadarSensor method) (RedlightSensor method) (SensorBase method) get_current_position() (RingBuffer method) get_current_route() (NavigationSensor method) get_current_time_step() (Player method) get_decoder() (PredictiveRepresentationLearner method) get_default_device() (in module alf.device_ctx) get_diff() (in module alf.utils.git_utils) get_disc_0_begin_position() (ReplayBuffer method) get_earliest_position() (RingBuffer method) get_env() (in module alf.config_helpers) (in module alf.utils.common) get_episode_begin_position() (ReplayBuffer method) get_epsilon_greedy() (in module alf.utils.common) get_features() (TestDataSet method) get_field() (in module alf.nest.nest) (ReplayBuffer method) get_gin_confg_strs() (in module alf.utils.common) get_gin_file() (in module alf.utils.common) get_global_counter() (in module alf.summary.summary_ops) get_goal_from_trajectory() (GoalReplayEnvWrapper method) get_handled_pre_configs() (in module alf.config_util) get_info() (AlfEnvironment method) (AlfEnvironmentBaseWrapper method) (AlfGymWrapper method)

get_initial_policy_state() (in module alf.utils.common) get_initial_predict_state() (Algorithm method) get_initial_rollout_state() (Algorithm method) get_initial_time_step() (in module alf.utils.common) get_initial_train_state() (Algorithm method) get_initial_transform_state() (Algorithm method) get_inoperative_configs() (in module alf.config_util) get_input_tensor_spec() (in module alf.networks.network) get_invertible() (in module alf.utils.dist_utils) get_lambda() (Generator method) get_metrics() (RLAlgorithm method) get_mode() (in module alf.utils.dist_utils) get_nest_batch_size() (in module alf.nest.nest) get_nest_shape() (in module alf.nest.nest) get_nest_size() (in module alf.nest.nest) get_nested_field() (in module alf.nest.utils) get_next_waypoint_index() (NavigationSensor method) get_num_tasks() (MultitaskWrapper method) get_observation_spec() (in module alf.config_helpers) (in module alf.utils.common) get_operative_configs() (in module alf.config_util) get_opt_arg() (in module alf.optimizers.utils) get_optimizer_info() (Algorithm method) get_outer_rank() (in module alf.nest.utils) get_overspeed_amount() (Player method) get_param_name() (Algorithm method) get_queue_size() (AsyncUnroller method) get_raw_observation_spec() (in module alf.config_helpers) (in module alf.utils.common) get_revision() (in module alf.utils.git_utils) get_reward_spec() (in module alf.config_helpers) (in module alf.utils.common) get_rmode() (in module alf.utils.dist_utils) get_scaled_image_size() (in module alf.environments.carla_sensors) get_single_observation() (BirdEyeTopDownEnv method) (VectorizedTopDownEnv method) get_state_specs() (DynamicsLearningAlgorithm method) get_states_shape() (in module alf.utils.common) get_step_metrics() (RLAlgorithm method) get_target_fields() (SimpleDecoder method) get_targets() (TestDataSet method) get_time_step_field() (Experience method) get_trajectory_with_goal() (GoalReplayEnvWrapper method) get_uniform_prior_logpi() (MdqCriticNetwork method) get_unique_num_actions() (in module alf.algorithms.mcts_models) get_unoptimized_parameter_info() (Algorithm method) get_unused_port() (in module alf.utils.common) get_vocab_size() (in module alf.utils.common) get_waypoint() (NavigationSensor method) get_waypoints() (World method) get_weather_fields() (WeatherParameters method) GetFields (class in alf.layers) GFT (class in alf.layers) global_counter (EvalJob attribute) (UnrollJob attribute) global_norm() (in module alf.utils.tensor_utils) gns (LossInfo attribute) GnssSensor (class in alf.environments.carla_sensors) goal (GoalInfo attribute) (GoalState attribute) goal_generator (AgentInfo attribute) (AgentState attribute) GoalInfo (class in alf.algorithms.goal_generator) GoalReplayEnvWrapper (class in alf.environments.alf_wrappers) GoalState (class in alf.algorithms.goal_generator) GoBoard (class in alf.environments.suite_go) GoEnvironment (class in alf.environments.suite_go) gpus (GridSearchConfig property) grad() (in module alf.nest.utils) GradientNoiseScaleEstimator (class in alf.optimizers.utils) GridSearch (class in alf.bin.grid_search) GridSearchConfig (class in alf.bin.grid_search) GRUCell (class in alf.networks.networks) gym (AlfGymWrapper property)

H

HandcraftedAlgorithm (class in alf.algorithms.handcrafted_algorithm) has_checkpoint() (Checkpointer method) has_data() (RingBuffer method) has_multidim_reward() (RLAlgorithm method) has_offline (Algorithm property) has_rsample (OneHotCategoricalGumbelSoftmax attribute) (TruncatedDistribution attribute)

has_space() (RingBuffer method) hidden_neurons (SimpleFC property) HindsightExperienceTransformer (class in alf.algorithms.data_transformer) histogram() (in module alf.summary.summary_ops) histogram_continuous() (in module alf.utils.summary_utils) histogram_discrete() (in module alf.utils.summary_utils) huber_function() (in module alf.utils.losses) HyperNetwork (class in alf.algorithms.hypernetwork_algorithm)

I

icdf() (CauchyITS static method) (InverseTransformSampling static method) (NormalITS static method) (T2ITS static method) ICMAlgorithm (class in alf.algorithms.icm_algorithm) ICMInfo (class in alf.algorithms.icm_algorithm) id (NumpyWaypoint attribute) Identity (class in alf.layers) identity() (in module alf.utils.math_ops) IdentityDataTransformer (class in alf.algorithms.data_transformer) Image (class in alf.summary.render) image_scale_transformer() (in module alf.utils.common) ImageChannelFirst (class in alf.environments.gym_wrappers) ImageDecodingNetwork (class in alf.networks.encoding_networks) ImageDecodingNetworkV2 (class in alf.networks.encoding_networks) ImageEncodingNetwork (class in alf.networks.encoding_networks) images() (in module alf.summary.summary_ops) ImageScaleTransformer (class in alf.algorithms.data_transformer) import_config() (in module alf.config_util) importance_weights (BatchInfo attribute) IMUSensor (class in alf.environments.carla_sensors) in_features (SimpleFC attribute) increment_global_counter() (in module alf.summary.summary_ops) ind_to_action() (ActionQuantizer method) info (AlgStep attribute) info() (in module alf.utils.common) info_once() (in module alf.utils.common) info_spec() (Player method) initial_collect_steps (MuzeroRepresentationTrainingOptions attribute) initial_inference() (MCTSModel method) initial_predict() (MCTSModel method) initial_priority (ReplayBuffer property) initial_representation() (MCTSModel method) initialize() (NeroPlus static method) initialize_bias() (DiscreteRegressionLoss method) (OrderedDiscreteRegressionLoss method) (ScalarPredictionLoss method) inoperative_config_str() (in module alf.utils.gin_utils) input_size (FC property) (NoisyFC property) input_tensor_spec (Network property) interp_color() (in module alf.environments.carla_sensors) interval (MuzeroRepresentationTrainingOptions attribute) (PPGAuxAlgorithm property) (PPGAuxOptions attribute) inverse() (NormalizingFlowNetwork method) inverse_loss (ICMInfo attribute) inverse_mvp (GeneratorLossInfo attribute) inverse_transform() (InvertibleTransform method) (Log1pTransform method) (Sqrt1pTransform method) (SqrtLinearTransform method) InverseMVPAlgorithm (class in alf.algorithms.generator) InverseTransformSampling (class in alf.utils.distributions)

InvertibleTransform (class in alf.utils.math_ops) IqlActionState (class in alf.algorithms.iql_algorithm) IqlActorInfo (class in alf.algorithms.iql_algorithm) IqlAlgorithm (class in alf.algorithms.iql_algorithm) IqlCriticInfo (class in alf.algorithms.iql_algorithm) IqlCriticState (class in alf.algorithms.iql_algorithm) IqlInfo (class in alf.algorithms.iql_algorithm) IqlLossInfo (class in alf.algorithms.iql_algorithm) IqlState (class in alf.algorithms.iql_algorithm) irm (AgentInfo attribute) (AgentState attribute) is_available() (in module alf.environments.suite_babyai) (in module alf.environments.suite_bsuite) (in module alf.environments.suite_carla) (in module alf.environments.suite_dmc) (in module alf.environments.suite_dmlab) (in module alf.environments.suite_highway) (in module alf.environments.suite_mario) (in module alf.environments.suite_socialbot) is_bounded() (BoundedTensorSpec class method) (TensorSpec class method) is_checkpoint_enabled() (in module alf.utils.checkpoint_utils) is_continuous (TensorSpec property) is_discrete (TensorSpec property) is_distributed (PerProcessContext property) is_distribution_output (Network property) is_eval() (in module alf.utils.common) is_first() (Experience method) (TimeStep method) is_full() (DataBuffer method) is_harsh_brake() (in module alf.environments.metadrive.extra_rewards) is_inside_docker_container() (in module alf.utils.common) is_junction (NumpyWaypoint attribute) is_last() (Experience method) (TimeStep method) is_mid() (Experience method) (TimeStep method) is_namedtuple() (in module alf.nest.nest) is_nested() (in module alf.nest.nest) is_partial_trajectory (ModelTarget attribute) is_pretrain() (in module alf.utils.common) is_rendering_enabled() (in module alf.summary.render) is_replay() (in module alf.utils.common) is_repo_root() (in module alf.utils.common) is_rl() (Algorithm method) (RLAlgorithm method) is_rnn (Network property) is_rollout() (in module alf.utils.common) is_running_red_light() (World method) is_same_spec() (in module alf.utils.spec_utils) is_summary_enabled() (in module alf.summary.summary_ops) is_training() (in module alf.utils.common) is_unnamedtuple() (in module alf.nest.nest) IterationsReturnReader (class in alf.utils.plot_tb_curves) IterationsSuccessReader (class in alf.utils.plot_tb_curves)

J

join() (Coordinator method)

joined (Coordinator property)

K

k (ActionRepeatState attribute) keep_closest_n() (Polyline method)

kl_wrt_prior (MdqCriticInfo attribute) kld (MoNetInfo attribute) (VAEInfo attribute)

L

l2_dist_close_reward_fn() (in module alf.algorithms.data_transformer) LagInfo (class in alf.algorithms.lagrangian_reward_weight_algorithm) LagrangianPredRewardWeightAlgorithm (class in alf.algorithms.lagrangian_reward_weight_algorithm) LagrangianRewardWeightAlgorithm (class in alf.algorithms.lagrangian_reward_weight_algorithm) Lambda (class in alf.layers) lane_change (NumpyLaneMarking attribute) (NumpyWaypoint attribute) lane_id (NumpyWaypoint attribute) lane_type (NumpyWaypoint attribute) lane_width (NumpyWaypoint attribute) LaneInvasionSensor (class in alf.environments.carla_sensors) LaneKeepingReward (class in alf.environments.metadrive.extra_rewards) LAST (StepType attribute) latent_vector (MBPState attribute) LatentActorDistributionNetwork (class in alf.networks.actor_distribution_networks) LatentMbrlAlgorithm (class in alf.algorithms.mbrl_algorithm) latest() (AverageEpisodicAggregationMetric method) (MetricBuffer method) launch_snapshot_gridsearch() (in module alf.bin.grid_search) launch_snapshot_play() (in module alf.bin.play) lean_function() (in module alf.utils.lean_function) LEFT (NoisyArray attribute) left_lane_marking (NumpyWaypoint attribute) LimitedDiscreteActions (class in alf.environments.mario_wrappers) LinearScheduler (class in alf.utils.schedulers) LinearTdStepFunc (class in alf.algorithms.muzero_representation_learner) load() (Checkpointer method) (in module alf.environments.suite_babyai) (in module alf.environments.suite_bsuite) (in module alf.environments.suite_carla) (in module alf.environments.suite_dmc) (in module alf.environments.suite_dmlab) (in module alf.environments.suite_go) (in module alf.environments.suite_gym) (in module alf.environments.suite_highway) (in module alf.environments.suite_mario) (in module alf.environments.suite_metadrive) (in module alf.environments.suite_procgen) (in module alf.environments.suite_simple) (in module alf.environments.suite_socialbot) (in module alf.environments.suite_tic_tac_toe) (MultitaskWrapper static method)

load_cifar10() (in module alf.utils.datagen) load_config() (in module alf.config_util) load_mnist() (in module alf.utils.datagen) load_offline_replay_buffer() (RLAlgorithm method) load_state_dict() (Algorithm method) load_test() (in module alf.utils.datagen) load_wikitext103() (in module alf.utils.datagen) load_wikitext2() (in module alf.utils.datagen) load_with_random_max_episode_steps() (in module alf.environments.utils) loc (DiagMultivariateCauchy property) (TruncatedDistribution property) location (NumpyWaypoint attribute) Log1pTransform (class in alf.utils.math_ops) log_abs_det_jacobian() (Softclip method) (Softplus method) (Softsign method) (StableTanh method) log_metrics() (in module alf.utils.common) log_pi (SacInfo attribute) log_prob (ActorCriticInfo attribute) (PPGRolloutInfo attribute) log_prob() (CauchyITS static method) (InverseTransformSampling static method) (NormalITS static method) (T2ITS static method) (TruncatedDistribution method) (TruncatedNormal method) Loss (class in alf.algorithms.algorithm) loss (DIAYNInfo attribute) (DynamicsInfo attribute) (EntropyTargetInfo attribute) (GoalInfo attribute) (LossInfo attribute) (MuzeroInfo attribute) (VAEInfo attribute) LossInfo (class in alf.data_structures) lower_bound (TruncatedDistribution property) LSTMCell (class in alf.networks.networks) LSTMEncodingNetwork (class in alf.networks.encoding_networks)

M

main() (in module alf.bin.compare) (in module alf.bin.grid_search) (in module alf.bin.play) (in module alf.bin.train) (in module alf.bin.verify_checkpoint) (in module alf.environments.carla_spectator) (in module alf.test.main) make_bird_eye_observation_renderer() (in module alf.environments.metadrive.renderer) make_ddp_performer() (in module alf.utils.distributed) make_experience() (in module alf.data_structures) make_gaussian() (MoNetAlgorithm static method) make_invertible_transform() (NormalizingFlowNetwork method) make_nested_module() (in module alf.nest.utils) make_parallel() (ActorDistributionNetworkBase method) (BetaProjectionNetwork method) (Branch method) (CategoricalProjectionNetwork method) (Conv2D method) (ConvTranspose2D method) (CriticNetwork method) (CriticRNNNetwork method) (DynamicsNetwork method) (Echo method) (ElementwiseLayerBase method) (EncodingNetwork method) (FC method) (LSTMEncodingNetwork method) (NestConcat method) (NestMultiply method) (NestOuterProduct method) (NestSum method) (Network method) (NetworkWrapper method) (NormalProjectionNetwork method) (OneHot method) (Parallel method) (Permute method) (QNetworkBase method) (Reshape method) (Sequential method) (Sum method) (Transpose method) (ValueNetworkBase method) make_parallel_input() (in module alf.layers) make_parallel_net() (in module alf.layers) make_parallel_spec() (in module alf.layers) make_vectorized_observation_renderer() (in module alf.environments.metadrive.renderer) map_structure() (in module alf.nest.nest) map_structure_up_to() (in module alf.nest.nest) map_structure_without_check() (in module alf.nest.nest) MapPolylinePerception (class in alf.environments.metadrive.map_perception) MarioXReward (class in alf.environments.mario_wrappers) mark_eval() (in module alf.utils.common) mark_pretrain() (in module alf.utils.common) mark_replay() (in module alf.utils.common) mark_rollout() (in module alf.utils.common) mask (MoNetInfo attribute) (PredictiveRepresentationLearnerInfo attribute) mask() (FIFOMemory method) mask_rec_loss (MoNetInfo attribute) max_n() (in module alf.utils.math_ops) max_worker_num (GridSearchConfig property) maximum (BoundedTensorSpec property) MaxSegmentTree (class in alf.experience_replayers.segment_tree) mba (MerlinLossInfo attribute) mba_info (MerlinInfo attribute) mba_state (MerlinState attribute) mbp (MerlinLossInfo attribute) mbp_info (MerlinInfo attribute) mbp_state (MerlinState attribute) MBPLossInfo (class in alf.algorithms.merlin_algorithm) MBPState (class in alf.algorithms.merlin_algorithm) MbrlAlgorithm (class in alf.algorithms.mbrl_algorithm) MbrlInfo (class in alf.algorithms.mbrl_algorithm) MbrlState (class in alf.algorithms.mbrl_algorithm) MCTSAlgorithm (class in alf.algorithms.mcts_algorithm) MCTSInfo (class in alf.algorithms.mcts_algorithm) MCTSModel (class in alf.algorithms.mcts_models) MCTSState (class in alf.algorithms.mcts_algorithm) MdqAlgorithm (class in alf.algorithms.mdq_algorithm) MdqAlphaInfo (class in alf.algorithms.mdq_algorithm) MdqCriticInfo (class in alf.algorithms.mdq_algorithm) MdqCriticNetwork (class in alf.networks.mdq_critic_networks) MdqCriticState (class in alf.algorithms.mdq_algorithm) MdqInfo (class in alf.algorithms.mdq_algorithm) MdqLossInfo (class in alf.algorithms.mdq_algorithm) MdqState (class in alf.algorithms.mdq_algorithm) mean (AffineTransformedDistribution property) mean() (MetricBuffer method) MeanCurve (class in alf.utils.plot_tb_curves) MeanCurveGroupReader (class in alf.utils.plot_tb_curves) MeanCurveReader (class in alf.utils.plot_tb_curves) MeanSquaredLoss (class in alf.utils.losses) mem_readout (MBPState attribute) members() (SequentialDataTransformer method) Memory (class in alf.networks.memory) memory (MBPState attribute) (MemoryBasedPredictor property) memory() (FIFOMemory method) MemoryBasedActor (class in alf.algorithms.merlin_algorithm) MemoryBasedPredictor (class in alf.algorithms.merlin_algorithm) MemoryWithUsage (class in alf.networks.memory) MerlinAlgorithm (class in alf.algorithms.merlin_algorithm) MerlinInfo (class in alf.algorithms.merlin_algorithm) MerlinLossInfo (class in alf.algorithms.merlin_algorithm) MerlinState (class in alf.algorithms.merlin_algorithm) metadata (BatchEnvironmentWrapper property) (DeepmindLabEnv attribute) (FastParallelEnvironment property) (GoEnvironment attribute) (ParallelAlfEnvironment property) MetricBuffer (class in alf.metrics.metrics) mi_estimator (GeneratorLossInfo attribute) MID (StepType attribute) MIEstimator (class in alf.algorithms.mi_estimator) min_n() (in module alf.utils.math_ops) mini_batch_length (MuzeroRepresentationTrainingOptions attribute) (PPGAuxOptions attribute) mini_batch_size (MuzeroRepresentationTrainingOptions attribute) (PPGAuxOptions attribute) minimum (BoundedTensorSpec property) MinSegmentTree (class in alf.experience_replayers.segment_tree) Mixed (ActionType attribute) MixedPolicyUnittestEnv (class in alf.environments.suite_unittest) MixtureProjectionNetwork (class in alf.networks.projection_networks) mode (Beta property) Mode (in module alf.algorithms.taac_algorithm) mode (OneHotCategoricalGumbelSoftmax property) (OneHotCategoricalStraightThrough property) (TruncatedDistribution property) model (MuzeroRepresentationImpl property) ModelOutput (class in alf.algorithms.mcts_models) ModelState (class in alf.algorithms.mcts_models) ModelTarget (class in alf.algorithms.mcts_models) module alf alf.algorithms alf.algorithms.actor_critic_algorithm alf.algorithms.actor_critic_loss alf.algorithms.agent alf.algorithms.agent_helpers alf.algorithms.algorithm alf.algorithms.algorithm_interface alf.algorithms.async_unroller alf.algorithms.bc_algorithm alf.algorithms.causal_bc_algorithm alf.algorithms.config alf.algorithms.containers alf.algorithms.data_transformer alf.algorithms.ddpg_algorithm alf.algorithms.decoding_algorithm alf.algorithms.diayn_algorithm alf.algorithms.dqn_algorithm alf.algorithms.dynamic_action_repeat_agent alf.algorithms.dynamics_learning_algorithm alf.algorithms.encoding_algorithm alf.algorithms.entropy_target_algorithm alf.algorithms.functional_particle_vi_algorithm alf.algorithms.generator alf.algorithms.goal_generator alf.algorithms.handcrafted_algorithm alf.algorithms.hypernetwork_algorithm alf.algorithms.icm_algorithm alf.algorithms.iql_algorithm alf.algorithms.lagrangian_reward_weight_algorithm alf.algorithms.mbrl_algorithm alf.algorithms.mcts_algorithm alf.algorithms.mcts_models alf.algorithms.mdq_algorithm alf.algorithms.merlin_algorithm alf.algorithms.mi_estimator alf.algorithms.monet_algorithm alf.algorithms.muzero_algorithm alf.algorithms.muzero_representation_learner alf.algorithms.oac_algorithm alf.algorithms.off_policy_algorithm alf.algorithms.on_policy_algorithm alf.algorithms.one_step_loss alf.algorithms.particle_vi_algorithm alf.algorithms.planning_algorithm alf.algorithms.ppg alf.algorithms.ppg.disjoint_policy_value_network alf.algorithms.ppg.ppg_aux_algorithm alf.algorithms.ppg.ppg_aux_phase_loss alf.algorithms.ppg.ppg_utils alf.algorithms.ppg_algorithm alf.algorithms.ppo_algorithm alf.algorithms.ppo_loss alf.algorithms.predictive_representation_learner alf.algorithms.prior_actor alf.algorithms.qrsac_algorithm alf.algorithms.reward_learning_algorithm alf.algorithms.rl_algorithm alf.algorithms.rnd_algorithm alf.algorithms.sac_algorithm alf.algorithms.sarsa_algorithm alf.algorithms.taac_algorithm alf.algorithms.td_loss alf.algorithms.trac_algorithm alf.algorithms.vae alf.algorithms.vq_vae alf.bin alf.bin.compare alf.bin.grid_search alf.bin.play alf.bin.train alf.bin.verify_checkpoint alf.config_helpers alf.config_util alf.data_structures alf.device_ctx alf.environments alf.environments.adv_fetch_envs alf.environments.alf_environment alf.environments.alf_gym3_wrapper alf.environments.alf_gym_wrapper alf.environments.alf_wrappers alf.environments.carla_controller alf.environments.carla_sensors alf.environments.carla_spectator alf.environments.dmc_gym_wrapper alf.environments.fast_parallel_environment alf.environments.gym_wrappers alf.environments.make_penv alf.environments.mario_wrappers alf.environments.metadrive alf.environments.metadrive.agent_perception alf.environments.metadrive.environments alf.environments.metadrive.extra_rewards alf.environments.metadrive.geometry alf.environments.metadrive.map_perception alf.environments.metadrive.renderer alf.environments.metadrive.sensors alf.environments.parallel_environment alf.environments.process_environment alf.environments.random_alf_environment alf.environments.simple alf.environments.simple.noisy_array alf.environments.simple.stochastic_with_risky_branch alf.environments.suite_babyai alf.environments.suite_bsuite alf.environments.suite_carla alf.environments.suite_dmc alf.environments.suite_dmlab alf.environments.suite_go alf.environments.suite_gym alf.environments.suite_highway alf.environments.suite_mario alf.environments.suite_metadrive alf.environments.suite_procgen alf.environments.suite_simple alf.environments.suite_socialbot alf.environments.suite_tic_tac_toe alf.environments.suite_unittest alf.environments.thread_environment alf.environments.utils alf.experience_replayers alf.experience_replayers.replay_buffer alf.experience_replayers.segment_tree alf.initializers alf.layers alf.metrics alf.metrics.metric alf.metrics.metrics alf.module alf.nest alf.nest.nest alf.nest.utils alf.networks alf.networks.action_encoder alf.networks.actor_distribution_networks alf.networks.actor_networks alf.networks.containers alf.networks.critic_networks alf.networks.dynamics_networks alf.networks.encoding_networks alf.networks.mdq_critic_networks alf.networks.memory alf.networks.network alf.networks.networks alf.networks.normalizing_flow_networks alf.networks.ou_process alf.networks.param_networks alf.networks.preprocessor_networks alf.networks.preprocessors alf.networks.projection_networks alf.networks.q_networks alf.networks.relu_mlp alf.networks.transformer_networks alf.networks.value_networks alf.norm_layers alf.optimizers alf.optimizers.adam_tf alf.optimizers.adamw alf.optimizers.nero_plus alf.optimizers.optimizers alf.optimizers.traj_optimizers alf.optimizers.trusted_updater alf.optimizers.utils alf.summary alf.summary.render alf.summary.summary_ops alf.tensor_specs alf.test alf.test.case alf.test.main alf.trainers alf.trainers.evaluator alf.trainers.policy_trainer alf.utils alf.utils.action_quantizer alf.utils.action_samplers alf.utils.averager alf.utils.checkpoint_utils alf.utils.common alf.utils.conditional_ops alf.utils.data_buffer alf.utils.datagen alf.utils.dist_utils alf.utils.distributed alf.utils.distributions alf.utils.external_configurables alf.utils.gin_utils alf.utils.git_utils alf.utils.lean_function alf.utils.losses alf.utils.math_ops alf.utils.normalizers alf.utils.per_process_context alf.utils.plot_tb_curves alf.utils.pretty_print alf.utils.process_coordinator alf.utils.schedulers alf.utils.sl_utils alf.utils.spec_utils alf.utils.summary_utils alf.utils.tensor_utils alf.utils.value_ops alf.utils.video_recorder alf.utils.visualizer

MoNetAlgorithm (class in alf.algorithms.monet_algorithm) MoNetInfo (class in alf.algorithms.monet_algorithm) MoNetUNet (class in alf.algorithms.monet_algorithm) mul_n() (in module alf.utils.math_ops) multi_quantile_huber_loss() (in module alf.utils.losses) MultinomialSampler (class in alf.utils.action_samplers) MultitaskWrapper (class in alf.environments.alf_wrappers) MuzeroAlgorithm (class in alf.algorithms.muzero_algorithm) MuzeroInfo (class in alf.algorithms.muzero_representation_learner) MuzeroRepresentationImpl (class in alf.algorithms.muzero_representation_learner) MuzeroRepresentationLearner (class in alf.algorithms.muzero_representation_learner) MuzeroRepresentationTrainingOptions (class in alf.algorithms.muzero_representation_learner)

N

NaiveParallelLayer (class in alf.layers) NaiveParallelNetwork (class in alf.networks.network) name (Algorithm property) (MeanCurveGroupReader property) (MeanCurveReader property) (Network property) (scope property) namedtuple() (in module alf.data_structures) NavigationSensor (class in alf.environments.carla_sensors) ndim (TensorSpec property) need_full_rollout_state() (Algorithm method) neg_entropy (ActorCriticLossInfo attribute) (EntropyTargetLossInfo attribute) (MdqAlphaInfo attribute) (SacActorInfo attribute) (SarsaInfo attribute) (SarsaLossInfo attribute) NeroPlus (class in alf.optimizers.nero_plus) (in module alf.optimizers.optimizers) nest_top_level() (in module alf.nest.nest) NestCombiner (class in alf.nest.utils) NestConcat (class in alf.nest.utils) NestedEntropyTargetAlgorithm (class in alf.algorithms.entropy_target_algorithm) NestMultiply (class in alf.nest.utils) NestOuterProduct (class in alf.nest.utils) NestSum (class in alf.nest.utils) Network (class in alf.networks.network) network (DynamicsState attribute) networks (Parallel property) NetworkWrapper (class in alf.networks.network) next_predicted_reward (MCTSState attribute) nnz (SumSegmentTree property) noise (SarsaState attribute) noise_dim (Generator property) NoisyArray (class in alf.environments.simple.noisy_array) NoisyFC (class in alf.networks.networks)

NonEpisodicAgent (class in alf.environments.alf_wrappers) NonEpisodicEnv (class in alf.environments.gym_wrappers) NormalITS (class in alf.utils.distributions) normalize() (Normalizer method) normalize_along_batch_dims() (in module alf.layers) normalize_min_max() (in module alf.utils.math_ops) NormalizedAction (class in alf.environments.gym_wrappers) NormalizedActionWrapper (class in alf.environments.alf_wrappers) Normalizer (class in alf.utils.normalizers) normalizer (RewardNormalizer property) NormalizingFlowNetwork (class in alf.networks.normalizing_flow_networks) NormalProjectionNetwork (class in alf.networks.projection_networks) normcdf() (in module alf.algorithms.prior_actor) num_components (MixtureProjectionNetwork property) num_environments (RingBuffer property) num_particles (HyperNetwork property) (ParVIAlgorithm property) num_processes (PerProcessContext property) num_replicas (DynamicsLearningAlgorithm property) num_spare_envs_for_reload (FastParallelEnvironment property) (ParallelAlfEnvironment property) num_tasks (AlfEnvironment property) (AlfEnvironmentBaseWrapper property) (BatchEnvironmentWrapper property) (FastParallelEnvironment property) (MultitaskWrapper property) (ParallelAlfEnvironment property) num_updates_per_train_iter (MuzeroRepresentationTrainingOptions attribute) (PPGAuxOptions attribute) num_waypoints (NavigationSensor property) NumberOfEpisodes (class in alf.metrics.metrics) numel (TensorSpec property) numpy_constant() (TensorSpec method) numpy_sample() (BoundedTensorSpec method) numpy_zeros() (TensorSpec method) NumpyLaneMarking (class in alf.environments.carla_sensors) NumpyWaypoint (class in alf.environments.carla_sensors)

O

OacAlgorithm (class in alf.algorithms.oac_algorithm) observation (Experience property) (ModelTarget attribute) (TracExperience attribute) (TracInfo attribute) observation() (BaseObservationWrapper method) (EpisodicRandomFrameCrop method) (FrameStack method) (ProcessFrame84 method) observation_desc() (BEVSensor method) (CameraSensor method) (CarlaEnvironment method) (CollisionSensor method) (DynamicObjectSensor method) (GnssSensor method) (GoEnvironment method) (IMUSensor method) (LaneInvasionSensor method) (NavigationSensor method) (ObstacleDetectionSensor method) (Player method) (RadarSensor method) (RedlightSensor method) (SensorBase method) (TicTacToeEnvironment method) observation_space (BSuiteWrapper property) (DMCGYMWrapper property) (VectorizedObservation property) observation_spec (AgentPerception property) (BirdEyeObservation property) (BirdEyeTopDownEnv property) (MapPolylinePerception property) (ProcessEnvironment attribute) (RLAlgorithm property) (VectorizedObservation property) (VectorizedTopDownEnv property) observation_spec() (ActionObservationWrapper method) (AlfEnvironment method) (AlfEnvironmentBaseWrapper method) (AlfGym3Wrapper method) (AlfGymWrapper method) (AlfMetaDriveWrapper method) (BatchEnvironmentWrapper method) (BEVSensor method) (CameraSensor method) (CarlaEnvironment method) (CollisionSensor method) (DynamicObjectSensor method) (FastParallelEnvironment method) (GnssSensor method) (GoEnvironment method) (IMUSensor method) (LaneInvasionSensor method) (MultitaskWrapper method) (NavigationSensor method) (ObstacleDetectionSensor method) (ParallelAlfEnvironment method) (Player method) (ProcessEnvironment method) (RadarSensor method) (RandomAlfEnvironment method) (RedlightSensor method) (SensorBase method) (ThreadEnvironment method) (TicTacToeEnvironment method) (UnittestEnv method)

ObservationNormalizer (class in alf.algorithms.data_transformer) observe() (AgentPerception method) (BirdEyeObservation method) (MapPolylinePerception method) (VectorizedObservation method) observe_for_aux_replay() (PPGAuxAlgorithm method) observe_for_metrics() (Algorithm method) observe_for_replay() (Algorithm method) (DynamicActionRepeatAgent method) ObstacleDetectionSensor (class in alf.environments.carla_sensors) obtain_solution() (CEMOptimizer method) (RandomOptimizer method) (TrajOptimizer method) OffPolicyAlgorithm (class in alf.algorithms.off_policy_algorithm) on_policy (Algorithm property) (AlgorithmInterface property) (OffPolicyAlgorithm property) (OnPolicyAlgorithm property) (PPOAlgorithm property) on_tick() (World method) ONE_MINUS (ReplayBuffer attribute) one_step_discounted_return() (in module alf.utils.value_ops) OneHot (class in alf.layers) OneHotCategoricalGumbelSoftmax (class in alf.utils.dist_utils) OnehotCategoricalProjectionNetwork (class in alf.networks.projection_networks) OneHotCategoricalStraightThrough (class in alf.utils.dist_utils) ones() (TensorSpec method) OneStepTDLoss (class in alf.algorithms.one_step_loss) OneStepTDQRLoss (class in alf.algorithms.one_step_loss) OnPolicyAlgorithm (class in alf.algorithms.on_policy_algorithm) optimizers() (Algorithm method) OrderedDiscreteRegressionLoss (class in alf.utils.losses) OUProcess (class in alf.networks.ou_process) (class in alf.utils.dist_utils) out_features (SimpleFC attribute) output (AlgStep attribute) output_channels (ParamLayerNorm property) output_size (FC property) (NoisyFC property) output_spec (DiscreteVAE property) (EncodingAlgorithm property) (MuzeroRepresentationLearner property) (Network property) (PredictiveRepresentationLearner property)

P

pack_image_nest() (Image class method) pack_sequence_as() (in module alf.nest.nest) Parallel (class in alf.networks.containers) ParallelActorDistributionNetwork (class in alf.networks.actor_distribution_networks) ParallelAlfEnvironment (class in alf.environments.parallel_environment) ParallelCategoricalProjectionNetwork (class in alf.networks.projection_networks) ParallelConv2D (class in alf.layers) ParallelConvTranspose2D (class in alf.layers) ParallelDynamicsNetwork (class in alf.networks.dynamics_networks) ParallelEncodingNetwork() (in module alf.networks.encoding_networks) ParallelFC (class in alf.layers) ParallelQNetwork (class in alf.networks.q_networks) ParallelValueNetwork (class in alf.networks.value_networks) param_keys (GridSearchConfig property) param_length (ParamConv2D property) (ParamConvNet property) (ParamFC property) (ParamLayerNorm property) (ParamNetwork property) param_values (GridSearchConfig property) ParamConv2D (class in alf.layers) ParamConvNet (class in alf.networks.param_networks) ParamFC (class in alf.layers) ParamLayerNorm (class in alf.norm_layers) ParamLayerNorm1d (class in alf.norm_layers) ParamLayerNorm2d (class in alf.norm_layers) ParamNetwork (class in alf.networks.param_networks) params_to_distributions() (in module alf.utils.dist_utils) paras_queue (PerProcessContext property) parse_conf_file() (in module alf.utils.common) parse_config() (in module alf.config_helpers) particles (ParVIAlgorithm property) ParVIAlgorithm (class in alf.algorithms.particle_vi_algorithm) path (Algorithm property) (AlgorithmInterface property) PENALTY_RATE_COLLISION (Player attribute) PENALTY_RATE_RED_LIGHT (Player attribute) PerformanceProfiler (class in alf.environments.alf_wrappers) Periodically (class in alf.utils.common) Permute (class in alf.layers) PerProcessContext (class in alf.utils.per_process_context) pformat_pycolor() (in module alf.utils.pretty_print) pg_loss (ActorCriticLossInfo attribute) PIDController (class in alf.environments.carla_controller) PlanAlgorithm (class in alf.algorithms.planning_algorithm) planner (MbrlInfo attribute) (MbrlState attribute) (PlannerInfo attribute) PlannerInfo (class in alf.algorithms.planning_algorithm) PlannerState (class in alf.algorithms.planning_algorithm) play() (in module alf.bin.play) Player (class in alf.environments.suite_carla) players (CarlaEnvironment property) plot() (CurvesPlotter method) point (Polyline attribute) policy_kl_loss (PPGAuxPhaseLossInfo attribute) policy_state (UnrollResult attribute) policy_step (UnrollResult attribute) PolicyUnittestEnv (class in alf.environments.suite_unittest) Polyline (class in alf.environments.metadrive.geometry) positions (BatchInfo attribute) PowerTransform (in module alf.utils.dist_utils) ppg_network_forward() (in module alf.algorithms.ppg.ppg_utils) PPGAlgorithm (class in alf.algorithms.ppg_algorithm) PPGAuxAlgorithm (class in alf.algorithms.ppg.ppg_aux_algorithm) PPGAuxOptions (class in alf.algorithms.ppg.ppg_aux_algorithm) PPGAuxPhaseLoss (class in alf.algorithms.ppg.ppg_aux_phase_loss) PPGAuxPhaseLossInfo (class in alf.algorithms.ppg.ppg_aux_phase_loss) PPGRolloutInfo (class in alf.algorithms.ppg.ppg_utils) PPGTrainInfo (class in alf.algorithms.ppg.ppg_utils) PPOAlgorithm (class in alf.algorithms.ppo_algorithm) PPOInfo (class in alf.algorithms.ppo_algorithm) PPOLoss (class in alf.algorithms.ppo_loss) pre_config() (in module alf.config_util) pre_loaded (Algorithm property) pred_state (MCTSState attribute) (ModelState attribute) pred_state_spec (MCTSModel property) predict_dataset() (in module alf.utils.sl_utils) predict_multi_step() (PredictiveRepresentationLearner method) predict_plan() (CEMPlanAlgorithm method) (PlanAlgorithm method) (RandomShootingAlgorithm method) predict_state_spec (Algorithm property) predict_step() (ActorCriticAlgorithm method) (Agent method) (AlgorithmInterface method) (BcAlgorithm method) (CausalBcAlgorithm method) (CriticAlgorithm method) (DdpgAlgorithm method) (DeterministicDynamicsAlgorithm method) (DynamicActionRepeatAgent method) (DynamicsLearningAlgorithm method) (EchoAlg method) (EncodingAlgorithm method) (EntropyTargetAlgorithm method) (FuncParVIAlgorithm method) (Generator method) (HandcraftedAlgorithm method) (HyperNetwork method) (ICMAlgorithm method) (InverseMVPAlgorithm method) (IqlAlgorithm method) (LagrangianPredRewardWeightAlgorithm method) (LagrangianRewardWeightAlgorithm method) (Loss method) (MbrlAlgorithm method) (MCTSAlgorithm method) (MdqAlgorithm method) (MemoryBasedActor method) (MemoryBasedPredictor method) (MerlinAlgorithm method) (MuzeroAlgorithm method) (MuzeroRepresentationImpl method) (MuzeroRepresentationLearner method) (NestedEntropyTargetAlgorithm method) (ParVIAlgorithm method) (PPGAlgorithm method) (PredictiveRepresentationLearner method) (RandomCategoricalGoalGenerator method) (RLAlgorithm method) (RLAlgWrapper method) (RNDAlgorithm method) (SacAlgorithm method) (SameActionPriorActor method) (SarsaAlgorithm method) (SGDEntropyTargetAlgorithm method) (SimpleDecoder method) (StochasticDynamicsAlgorithm method) (TaacAlgorithmBase method) (TracAlgorithm method) (UniformPriorActor method) (Vqvae method)

prediction_model() (MCTSModel method) (SimpleMCTSModel method) PredictiveRepresentationLearner (class in alf.algorithms.predictive_representation_learner) PredictiveRepresentationLearnerInfo (class in alf.algorithms.predictive_representation_learner) prepare_rnn_batch_norm() (in module alf.norm_layers) preprocess_experience() (Agent method) (AlgorithmContainer method) (AlgorithmInterface method) (DynamicActionRepeatAgent method) (EchoAlg method) (MuzeroAlgorithm method) (MuzeroRepresentationImpl method) (MuzeroRepresentationLearner method) (PPOAlgorithm method) (PredictiveRepresentationLearner method) (RLAlgWrapper method) (TracAlgorithm method) PreprocessorNetwork (class in alf.networks.preprocessor_networks) pretrain_context (class in alf.utils.common) PrettyPrinter (class in alf.utils.pretty_print) prev_action (Experience property) (TracExperience attribute) (TracInfo attribute) prev_frames (FrameStackState attribute) prev_observation (SarsaState attribute) prev_plan (PlannerState attribute) prev_reward_sum (ModelState attribute) prev_step_type (SarsaState attribute) prev_tau (TaacInfo attribute) priority (LossInfo attribute) priority_replay (MuzeroRepresentationTrainingOptions attribute) priority_replay_alpha (MuzeroRepresentationTrainingOptions attribute) priority_replay_beta (MuzeroRepresentationTrainingOptions attribute) Process (class in alf.utils.process_coordinator) process() (ProcessFrame84 static method) process_call() (in module alf.environments.process_environment) processed_experience_spec (Algorithm property) ProcessEnvironment (class in alf.environments.process_environment) ProcessFrame84 (class in alf.environments.mario_wrappers) progress() (Scheduler method) (Trainer static method) prune_nest_like() (in module alf.nest.nest) push_summary_writer (class in alf.summary.summary_ops) py_assert_same_structure() (in module alf.nest.nest) py_flatten() (in module alf.nest.nest) py_flatten_up_to() (in module alf.nest.nest) py_map_structure() (in module alf.nest.nest) py_map_structure_up_to() (in module alf.nest.nest) py_map_structure_with_path() (in module alf.nest.nest) py_pack_sequence_as() (in module alf.nest.nest) py_prune_nest_like() (in module alf.nest.nest)

Q

q_values (DdpgCriticInfo attribute) q_values2 (ActPredOutput attribute) QNetwork (class in alf.networks.q_networks) QNetworkBase (class in alf.networks.q_networks)

QRNNNetwork (class in alf.networks.q_networks) QrsacAlgorithm (class in alf.algorithms.qrsac_algorithm) QuantileRegressionLoss (class in alf.utils.losses) quantization (VqvaeLossInfo attribute)

R

RadarSensor (class in alf.environments.carla_sensors) raise_requested_exception() (Coordinator method) rand() (TensorSpec method) randn() (TensorSpec method) RandomAlfEnvironment (class in alf.environments.random_alf_environment) RandomCategoricalGoalGenerator (class in alf.algorithms.goal_generator) RandomCrop (class in alf.layers) RandomFirstEpisodeLength (class in alf.environments.alf_wrappers) RandomOptimizer (class in alf.optimizers.traj_optimizers) RandomShootingAlgorithm (class in alf.algorithms.planning_algorithm) read() (FIFOMemory method) (Memory method) (MemoryWithUsage method) read_conf_file() (in module alf.utils.common) RealNVPNetwork (class in alf.networks.normalizing_flow_networks) rec_loss (MoNetInfo attribute) reconstruction (VqvaeLossInfo attribute) record_if (class in alf.summary.summary_ops) record_time (class in alf.utils.summary_utils) recurrent_inference() (MCTSModel method) RED_LIGHT_ENFORCE_DISTANCE (World attribute) RedlightSensor (class in alf.environments.carla_sensors) register_algorithm() (AgentHelper method) register_process() (Coordinator method) regression_loss() (in module alf.utils.sl_utils) ReluMLP (class in alf.networks.relu_mlp) remove_up_to() (RingBuffer method) RemoveActionEnvInfo (class in alf.environments.suite_highway) render() (AlfEnvironment method) (AlfEnvironmentBaseWrapper method) (AlfGym3Wrapper method) (AlfGymWrapper method) (AlfMetaDriveWrapper method) (BatchEnvironmentWrapper method) (BEVSensor method) (BirdEyeTopDownEnv method) (CameraSensor method) (CarlaEnvironment method) (DeepmindLabEnv method) (DMCGYMWrapper method) (DynamicObjectSensor method) (FastParallelEnvironment method) (GoEnvironment method) (NoisyArray method) (ParallelAlfEnvironment method) (Player method) (ProcessEnvironment method) (RandomAlfEnvironment method) (Renderer method) (StochasticWithRiskyBranch method) (ThreadEnvironment method) (TicTacToeEnvironment method) (VectorizedTopDownEnv method) render_action() (in module alf.summary.render) render_action_distribution() (in module alf.summary.render) render_bar() (in module alf.summary.render) render_contour() (in module alf.summary.render) render_curve() (in module alf.summary.render) render_heatmap() (in module alf.summary.render) render_text() (in module alf.summary.render) Renderer (class in alf.environments.metadrive.renderer) repeats (GridSearchConfig property) (TaacInfo attribute) (TaacState attribute) replace() (BoundedTensorSpec method) (TensorSpec method) replay_buffer (BatchInfo attribute) replay_buffer_length (MuzeroRepresentationTrainingOptions attribute) replay_context (class in alf.utils.common) ReplayBuffer (class in alf.experience_replayers.replay_buffer) ReplicationPad2d (class in alf.layers) repr (ActionRepeatState attribute) (AgentInfo attribute) (AgentState attribute) (BasicRolloutInfo attribute) repr_spec (MCTSModel property) (SimpleMCTSModel property) repr_wrapper() (in module alf.config_util) request_stop() (Coordinator method) reset() (AgentPerception method) (AlfEnvironment method) (AverageEpisodicAggregationMetric method) (BabyAIWrapper method) (BSuiteWrapper method) (DeepmindLabEnv method) (DMAtariPreprocessing method) (DMCGYMWrapper method) (DynamicObjectSensor method) (EgoKinematicReward method) (EnvironmentSteps method) (EpisodicRandomFrameCrop method) (ExtraReward method) (FrameFlip method) (FrameFormat method) (FrameSkip method) (FrameStack method) (MapPolylinePerception method) (MarioXReward method) (MemoryWithUsage method) (NoisyArray method) (NumberOfEpisodes method) (PIDController method) (Player method) (ProcessEnvironment method) (StepMetric method) (StochasticWithRiskyBranch method) (TrajOptimizer method) (VectorizedObservation method) (VehicleController method) reset_board() (GoBoard method) reset_configs() (in module alf.config_util) reset_global_counter() (in module alf.summary.summary_ops) reset_net_parameters() (CriticAlgorithm method) reset_parameters() (Branch method) (CausalConv1D method) (CompositionalFC method) (Conv2D method) (Conv2DBatchEnsemble method) (ConvTranspose2D method) (FC method) (FCBatchEnsemble method) (GFT method) (in module alf.layers) (NaiveParallelLayer method) (NoisyFC method) (ParallelConv2D method) (ParallelFC method) (Sequential method) (TransformerBlock method) reset_state() (AdamTF method) reset_state_if_necessary() (in module alf.utils.common) Reshape (class in alf.layers) Residue (class in alf.networks.networks) ResidueBlock (class in alf.layers)

residuIL_loss() (CausalBcAlgorithm method) resize() (Image method) ResnetDecodingNetwork (class in alf.algorithms.merlin_algorithm) ResnetEncodingNetwork (class in alf.algorithms.merlin_algorithm) restart() (in module alf.data_structures) result() (AverageEpisodicAggregationMetric method) (EnvironmentSteps method) (NumberOfEpisodes method) (StepMetric method) returns (PPOInfo attribute) reverse_cumprod() (in module alf.utils.tensor_utils) reverse_cumsum() (in module alf.utils.tensor_utils) revive() (RingBuffer method) reward (ActorCriticInfo attribute) (DdpgInfo attribute) (Experience property) (IqlInfo attribute) (MbrlInfo attribute) (MbrlState attribute) (MdqInfo attribute) (ModelOutput attribute) (ModelTarget attribute) (PPGRolloutInfo attribute) (PPOInfo attribute) (SacInfo attribute) (SarsaInfo attribute) (TaacInfo attribute) REWARD_COLLISION (Player attribute) REWARD_DIMENSION (Player attribute) REWARD_DISTANCE (Player attribute) REWARD_OVERALL (Player attribute) REWARD_OVERSPEED (Player attribute) reward_pred (ModelOutput attribute) REWARD_RED_LIGHT (Player attribute) reward_spec() (AlfEnvironment method) (AlfEnvironmentBaseWrapper method) (AlfGymWrapper method) (BatchEnvironmentWrapper method) (CarlaEnvironment method) (FastParallelEnvironment method) (MultitaskWrapper method) (ParallelAlfEnvironment method) (Player method) (ProcessEnvironment method) (ScalarRewardWrapper method) (ThreadEnvironment method) (UnittestEnv method) REWARD_SUCCESS (Player attribute) reward_weights (ActorCriticInfo attribute) (LagrangianRewardWeightAlgorithm property) (PPGRolloutInfo attribute) (PPOInfo attribute) (RLAlgorithm property) RewardClipping (class in alf.algorithms.data_transformer) RewardEstimationAlgorithm (class in alf.algorithms.reward_learning_algorithm) RewardNormalizer (class in alf.algorithms.data_transformer) rewards (AgentInfo attribute) (BasicRolloutInfo attribute) RewardScaling (class in alf.algorithms.data_transformer) RewardShifting (class in alf.algorithms.data_transformer) RewardTransformer (class in alf.algorithms.data_transformer) RIGHT (NoisyArray attribute) right_lane_marking (NumpyWaypoint attribute) RingBuffer (class in alf.utils.data_buffer) rl (ActionRepeatState attribute) (AgentInfo attribute) (AgentState attribute) (BasicRolloutInfo attribute) rl_discount (ActionRepeatState attribute) rl_reward (ActionRepeatState attribute) RLAlgorithm (class in alf.algorithms.rl_algorithm) RLAlgWrapper (class in alf.algorithms.containers) RLTrainer (class in alf.trainers.policy_trainer) RNDAlgorithm (class in alf.algorithms.rnd_algorithm) rnn_state (MBPState attribute) RNNPolicyUnittestEnv (class in alf.environments.suite_unittest) road_id (NumpyWaypoint attribute) rollout_action_distribution (PPOInfo attribute) rollout_b (TaacInfo attribute) rollout_context (class in alf.utils.common) rollout_info_spec (RLAlgorithm property) rollout_log_prob (PPOInfo attribute) rollout_reward (LagInfo attribute) rollout_state_spec (Algorithm property) rollout_step() (ActorCriticAlgorithm method) (Agent method) (AlgorithmInterface method) (DdpgAlgorithm method) (DIAYNAlgorithm method) (DqnAlgorithm method) (DynamicActionRepeatAgent method) (EchoAlg method) (EncodingAlgorithm method) (EntropyTargetAlgorithm method) (HandcraftedAlgorithm method) (ICMAlgorithm method) (IqlAlgorithm method) (LagrangianRewardWeightAlgorithm method) (Loss method) (MbrlAlgorithm method) (MCTSAlgorithm method) (MdqAlgorithm method) (MemoryBasedActor method) (MerlinAlgorithm method) (MuzeroAlgorithm method) (MuzeroRepresentationImpl method) (MuzeroRepresentationLearner method) (NestedEntropyTargetAlgorithm method) (OacAlgorithm method) (PPGAlgorithm method) (PredictiveRepresentationLearner method) (RandomCategoricalGoalGenerator method) (RLAlgWrapper method) (RNDAlgorithm method) (SacAlgorithm method) (SameActionPriorActor method) (SarsaAlgorithm method) (SGDEntropyTargetAlgorithm method) (TaacAlgorithmBase method) (TracAlgorithm method) (UniformPriorActor method) rotation (NumpyWaypoint attribute) route_resolution (World property) rsample() (Beta method) (OneHotCategoricalGumbelSoftmax method) (StableCauchy method) (TruncatedDistribution method) (TruncatedNormal method) rsample_action_distribution() (in module alf.utils.dist_utils) run() (GridSearch method) (Process method) run_loop() (Process method) run_under_record_context() (in module alf.utils.common) rw (AgentInfo attribute) (AgentState attribute)

S

SacActionState (class in alf.algorithms.sac_algorithm) SacActorInfo (class in alf.algorithms.sac_algorithm) SacAlgorithm (class in alf.algorithms.sac_algorithm) SacCriticInfo (class in alf.algorithms.sac_algorithm) SacCriticState (class in alf.algorithms.sac_algorithm) SacInfo (class in alf.algorithms.sac_algorithm) SacLossInfo (class in alf.algorithms.sac_algorithm) SacState (class in alf.algorithms.sac_algorithm) safe_mean_hist_summary() (in module alf.utils.summary_utils) safe_mean_summary() (in module alf.utils.summary_utils) SameActionPriorActor (class in alf.algorithms.prior_actor) sample() (BoundedTensorSpec method) (TruncatedNormal method) sample_action_distribution() (in module alf.utils.dist_utils) sample_parameters() (HyperNetwork method) sample_rewards (ActionRepeatState attribute) SarsaAlgorithm (class in alf.algorithms.sarsa_algorithm) SarsaInfo (class in alf.algorithms.sarsa_algorithm) SarsaLossInfo (class in alf.algorithms.sarsa_algorithm) SarsaState (class in alf.algorithms.sarsa_algorithm) save() (Checkpointer method) save_config() (in module alf.config_util) saved_args (Network property) scalar() (in module alf.summary.summary_ops) scalar_loss (LossInfo attribute) ScalarAdaptiveAverager (class in alf.utils.averager) ScalarAdaptiveNormalizer (class in alf.utils.normalizers) ScalarEMAverager (class in alf.utils.averager) ScalarEMNormalizer (class in alf.utils.normalizers) ScalarPredictionLoss (class in alf.utils.losses) ScalarRewardWrapper (class in alf.environments.alf_wrappers) ScalarWindowAverager (class in alf.utils.averager) ScalarWindowNormalizer (class in alf.utils.normalizers) Scale (class in alf.layers) scale (DiagMultivariateCauchy property) (TruncatedDistribution property) scale_gradient() (in module alf.utils.tensor_utils) scale_to_spec() (in module alf.utils.spec_utils) ScaleGradient (class in alf.layers) Scheduler (class in alf.utils.schedulers) scope (class in alf.summary.summary_ops) scope_name() (in module alf.summary.summary_ops) search() (in module alf.bin.grid_search) section_id (NumpyWaypoint attribute) seed() (AlfEnvironment method) (AlfEnvironmentBaseWrapper method) (AlfGymWrapper method) (AlfMetaDriveWrapper method) (BatchEnvironmentWrapper method) (DeepmindLabEnv method) (DMCGYMWrapper method) (FastParallelEnvironment method) (MultitaskWrapper method) (ParallelAlfEnvironment method) (RandomAlfEnvironment method) (ThreadEnvironment method) SegmentTree (class in alf.experience_replayers.segment_tree) select_from_mask() (in module alf.utils.conditional_ops) SensorBase (class in alf.environments.carla_sensors) Sequential (class in alf.layers) Sequential() (in module alf.networks.containers) SequentialAlg() (in module alf.algorithms.containers) SequentialDataTransformer (class in alf.algorithms.data_transformer) set_action_sequence_cost_func() (PlanAlgorithm method) set_batch_norm_current_step() (in module alf.norm_layers) set_batch_norm_max_steps() (in module alf.norm_layers) set_data_loader() (FuncParVIAlgorithm method) (HyperNetwork method) set_default_device() (in module alf.device_ctx) set_default_writer() (in module alf.summary.summary_ops) set_destination() (NavigationSensor method) set_distributed() (PerProcessContext method) set_exe_mode() (in module alf.utils.common) set_field() (in module alf.nest.nest) set_global_counter() (in module alf.summary.summary_ops) set_global_env() (in module alf.utils.common) set_latent_predictive_representation_module() (LatentMbrlAlgorithm method) set_model() (MCTSAlgorithm method) set_num_particles() (HyperNetwork method) set_on_policy() (Algorithm method) (AlgorithmContainer method) (AlgorithmInterface method) (EchoAlg method) (RLAlgWrapper method) set_parameters() (ParamConv2D method) (ParamConvNet method) (ParamFC method) (ParamLayerNorm method) (ParamNetwork method) set_paras_queue() (PerProcessContext method) set_path() (Agent method) (AgentHelper method) (Algorithm method) (AlgorithmContainer method) (AlgorithmInterface method) (EchoAlg method) (MuzeroAlgorithm method) (RLAlgWrapper method) set_random_seed() (in module alf.utils.common) set_replay_buffer() (Algorithm method) set_reward_weights() (RLAlgorithm method) set_transformed_observation_spec() (in module alf.utils.common) setUp() (TestCase method) SGD (in module alf.optimizers.optimizers) SGDEntropyTargetAlgorithm (class in alf.algorithms.entropy_target_algorithm) shape (Image property) (TensorSpec property) should_record_summaries() (in module alf.summary.summary_ops) should_stop() (Coordinator method) should_summarize_output() (in module alf.summary.summary_ops) SHOULDERS (LimitedDiscreteActions attribute) shuffle() (in module alf.utils.math_ops) SigmoidTransform (in module alf.utils.dist_utils) sign (Softclip attribute) (Softplus attribute) (Softsign attribute) (StableTanh attribute) SimpleActionEncoder (class in alf.networks.action_encoder) SimpleAttention (class in alf.layers) SimpleCarlaAlgorithm (class in alf.algorithms.handcrafted_algorithm) SimpleDataTransformer (class in alf.algorithms.data_transformer) SimpleDecoder (class in alf.algorithms.predictive_representation_learner) SimpleFC (class in alf.networks.relu_mlp) SimpleMCTSModel (class in alf.algorithms.mcts_models) SimplePredictionNet (class in alf.algorithms.mcts_models) singleton() (Network method) size (CategoryEncoder property) (Memory property) SLTrainer (class in alf.trainers.policy_trainer) snapshot_repo_roots() (in module alf.utils.common) SocialAttentionNetwork (class in alf.networks.transformer_networks) Softclip (class in alf.utils.dist_utils) softclip() (in module alf.utils.math_ops) softclip_tf() (in module alf.utils.math_ops) SoftclipTF() (in module alf.utils.dist_utils)

Softlower() (in module alf.utils.dist_utils) softlower() (in module alf.utils.math_ops) SoftmaxTransform (in module alf.utils.dist_utils) Softplus (class in alf.utils.dist_utils) Softsign (class in alf.utils.dist_utils) (class in alf.utils.math_ops) softsign() (in module alf.utils.math_ops) Softsign_ (class in alf.utils.math_ops) softsign_() (in module alf.utils.math_ops) Softupper() (in module alf.utils.dist_utils) softupper() (in module alf.utils.math_ops) spatial_broadcast() (in module alf.utils.tensor_utils) SpatialBroadcastDecodingNetwork() (in module alf.networks.encoding_networks) spec_means_and_magnitudes() (in module alf.utils.spec_utils) Sqrt1pTransform (class in alf.utils.math_ops) SqrtLinearTransform (class in alf.utils.math_ops) square() (in module alf.utils.math_ops) squared_brake_cost() (in module alf.environments.metadrive.extra_rewards) squared_jerk_cost() (in module alf.environments.metadrive.extra_rewards) SquareLoss (class in alf.utils.losses) StableCauchy (class in alf.utils.dist_utils) StableNormalProjectionNetwork (class in alf.networks.projection_networks) StableTanh (class in alf.utils.dist_utils) stack_images() (Image class method) stack_nests() (in module alf.nest.utils) stack_size (DataTransformer property) (FrameStacker property) (SequentialDataTransformer property) start() (FastParallelEnvironment method) (ParallelAlfEnvironment method) (ProcessEnvironment method) start_loop() (Process method) state (AlgStep attribute) (ModelOutput attribute) (ModelState attribute) (TracExperience attribute) (TracInfo attribute) state_dict (EvalJob attribute) (UnrollJob attribute) state_dict() (Algorithm method) state_spec (ActorDistributionNetworkBase property) (ActorNetworkBase property) (DataTransformer property) (Memory property) (Network property) (OUProcess property) (ParallelActorDistributionNetwork property) (ParallelQNetwork property) (ParallelValueNetwork property) (QNetworkBase property) (TransformerNetwork property) (ValueNetworkBase property) state_specs() (AgentHelper method) states (FIFOMemory property) (MemoryWithUsage property) stddev (AffineTransformedDistribution property) (DiagMultivariateNormal property) step (ModelState attribute) step() (ActionScalarization method) (AdamTF method) (AdamW method) (AlfEnvironment method) (BabyAIWrapper method) (BSuiteWrapper method) (DeepmindLabEnv method) (DMAtariPreprocessing method) (DMCGYMWrapper method) (FrameFormat method) (FrameSkip method) (MarioXReward method) (NeroPlus method) (NoisyArray method) (NonEpisodicEnv method) (PIDController method) (ProcessEnvironment method) (RemoveActionEnvInfo method) (StochasticWithRiskyBranch method) step_metrics (EvalJob attribute) (UnrollJob attribute) step_time (UnrollResult attribute) step_type (ActorCriticInfo attribute) (DdpgInfo attribute) (EntropyTargetInfo attribute) (Experience property) (ICMInfo attribute) (IqlInfo attribute) (MdqInfo attribute) (PPGRolloutInfo attribute) (PPOInfo attribute) (SacInfo attribute) (SarsaInfo attribute) (TaacInfo attribute) (TracExperience attribute) StepMetric (class in alf.metrics.metric) steps (ActionRepeatState attribute) (FrameStackState attribute) (MCTSState attribute) steps_to_episode_end() (ReplayBuffer method) StepScheduler (class in alf.utils.schedulers) StepType (class in alf.data_structures) StochasticDynamicsAlgorithm (class in alf.algorithms.dynamics_learning_algorithm) StochasticWithRiskyBranch (class in alf.environments.simple.stochastic_with_risky_branch) stop() (CarlaServer method) (RingBuffer method) stop_loop() (Process method) stop_on_exception() (Coordinator method) Sum (class in alf.layers) sum_nest() (in module alf.nest.nest) sum_to_leftmost() (in module alf.utils.math_ops) summarize_action() (in module alf.utils.summary_utils) summarize_config() (in module alf.utils.common) summarize_distribution() (in module alf.utils.summary_utils) summarize_distribution_gradient() (in module alf.utils.summary_utils) summarize_gin_config() (in module alf.utils.common) summarize_gradients() (in module alf.utils.summary_utils) summarize_loss() (in module alf.utils.summary_utils) summarize_metrics() (RLAlgorithm method) summarize_nest() (in module alf.utils.summary_utils) summarize_per_category_loss() (in module alf.utils.summary_utils) summarize_reward() (RLAlgorithm method) summarize_rollout() (Agent method) (RLAlgorithm method) (TaacAlgorithmBase method) summarize_tensor_gradients() (in module alf.utils.summary_utils) summarize_train() (Algorithm method) (DynamicActionRepeatAgent method) (FuncParVIAlgorithm method) (HyperNetwork method) (RLAlgorithm method) summarize_variables() (in module alf.utils.summary_utils) SummarizeGradient (class in alf.layers) summary() (SegmentTree method) SumSegmentTree (class in alf.experience_replayers.segment_tree) swish() (in module alf.utils.math_ops) sync_net() (MdqCriticNetwork method) SyncEvaluator (class in alf.trainers.evaluator)

T

t2cdf() (in module alf.utils.distributions) T2Cdf_ (class in alf.utils.distributions) T2ITS (class in alf.utils.distributions) TaacActorInfo (class in alf.algorithms.taac_algorithm) TaacAlgorithm (class in alf.algorithms.taac_algorithm) TaacAlgorithmBase (class in alf.algorithms.taac_algorithm) TaacCriticInfo (class in alf.algorithms.taac_algorithm) TaacInfo (class in alf.algorithms.taac_algorithm) TaacLAlgorithm (class in alf.algorithms.taac_algorithm) TaacLossInfo (class in alf.algorithms.taac_algorithm) TaacQAlgorithm (class in alf.algorithms.taac_algorithm) TaacState (class in alf.algorithms.taac_algorithm) TAACTDLoss (class in alf.algorithms.taac_algorithm) target (BcInfo attribute) (MuzeroInfo attribute) (PredictiveRepresentationLearnerInfo attribute) target_actor (DdpgCriticState attribute) target_critic (MdqCriticState attribute) (SacCriticInfo attribute) (TaacCriticInfo attribute) target_critic_free_form (MdqCriticInfo attribute) target_critics (DdpgCriticState attribute) (IqlCriticState attribute) (SacCriticState attribute) (SarsaInfo attribute) (SarsaState attribute) target_q_values (DdpgCriticInfo attribute) target_value (IqlCriticInfo attribute) TargetUpdater (class in alf.utils.common) task_names (AlfEnvironment property) (AlfEnvironmentBaseWrapper property) (BatchEnvironmentWrapper property) (FastParallelEnvironment property) (MultitaskWrapper property) (ParallelAlfEnvironment property) Tau (class in alf.algorithms.taac_algorithm) tau (TaacInfo attribute) (TaacState attribute) taus (ActPredOutput attribute) td_loss (ActorCriticLossInfo attribute) td_loss_actual (PPGAuxPhaseLossInfo attribute) td_loss_aux (PPGAuxPhaseLossInfo attribute) TDLoss (class in alf.algorithms.td_loss) TDQRLoss (class in alf.algorithms.td_loss) TemporallyCorrelatedNoiseWrapper (class in alf.environments.alf_wrappers) TemporalPool (class in alf.networks.networks) tensor_extend() (in module alf.utils.tensor_utils) tensor_extend_new_dim() (in module alf.utils.tensor_utils) tensor_extend_zero() (in module alf.utils.tensor_utils) tensor_prepend() (in module alf.utils.tensor_utils) tensor_prepend_zero() (in module alf.utils.tensor_utils) tensor_spec_from_gym_space() (in module alf.environments.alf_gym_wrapper) TensorSpec (class in alf.tensor_specs) termination() (in module alf.data_structures) TestCase (class in alf.test.case) TestDataSet (class in alf.utils.datagen) text() (in module alf.summary.summary_ops) ThreadEnvironment (class in alf.environments.thread_environment) tick() (EnsureSummary method) TicTacToeEnvironment (class in alf.environments.suite_tic_tac_toe) time_step (UnrollResult attribute) time_step_spec (ProcessEnvironment attribute) time_step_spec() (ActionObservationWrapper method) (AlfEnvironment method) (AlfEnvironmentBaseWrapper method) (AlfGymWrapper method) (BatchEnvironmentWrapper method) (DiscreteActionWrapper method) (FastParallelEnvironment method) (in module alf.data_structures) (NormalizedActionWrapper method) (ParallelAlfEnvironment method) (ProcessEnvironment method) (ScalarRewardWrapper method) TimeLimit (class in alf.environments.alf_wrappers) TimeStep (class in alf.data_structures) to_distribution_param_spec() (in module alf.utils.dist_utils) to_feature() (Polyline method) to_tensor() (in module alf.utils.tensor_utils) torch_dtype_to_str() (in module alf.tensor_specs) total_size (ReplayBuffer property) TracAlgorithm (class in alf.algorithms.trac_algorithm) trace_route() (World method) TracExperience (class in alf.algorithms.trac_algorithm) TracInfo (class in alf.algorithms.trac_algorithm) train() (Trainer method) train_from_replay_buffer() (Algorithm method) (AlgorithmInterface method) train_from_unroll() (Algorithm method) (AlgorithmInterface method) train_info_spec (Algorithm property) train_iter() (AlgorithmInterface method) (FuncParVIAlgorithm method) (HyperNetwork method) (RLAlgorithm method) train_state_spec (Algorithm property) train_step() (Agent method) (AlgorithmInterface method) (DdpgAlgorithm method) (DecodingAlgorithm method) (DeterministicDynamicsAlgorithm method) (DIAYNAlgorithm method) (DynamicActionRepeatAgent method) (DynamicsLearningAlgorithm method) (EchoAlg method) (EncodingAlgorithm method) (EntropyTargetAlgorithm method) (FixedRewardFunction method) (FuncParVIAlgorithm method) (Generator method) (HandcraftedAlgorithm method) (HyperNetwork method) (ICMAlgorithm method) (IqlAlgorithm method) (LatentMbrlAlgorithm method) (Loss method) (MbrlAlgorithm method) (MdqAlgorithm method) (MemoryBasedPredictor method) (MIEstimator method) (MoNetAlgorithm method) (MuzeroAlgorithm method) (MuzeroRepresentationImpl method) (MuzeroRepresentationLearner method) (NestedEntropyTargetAlgorithm method) (OnPolicyAlgorithm method) (ParVIAlgorithm method) (PlanAlgorithm method) (PPGAlgorithm method) (PPGAuxAlgorithm method) (PPOAlgorithm method) (PredictiveRepresentationLearner method) (RandomCategoricalGoalGenerator method) (RandomShootingAlgorithm method) (RewardEstimationAlgorithm method) (RLAlgWrapper method) (RNDAlgorithm method) (SacAlgorithm method) (SameActionPriorActor method) (SarsaAlgorithm method) (SGDEntropyTargetAlgorithm method) (SimpleDecoder method) (StochasticDynamicsAlgorithm method) (TaacAlgorithmBase method) (TracAlgorithm method) (UniformPriorActor method) (VariationalAutoEncoder method) (Vqvae method) train_step_offline() (Agent method) (Algorithm method) (AlgorithmInterface method) (BcAlgorithm method) (CausalBcAlgorithm method) Trainer (class in alf.trainers.policy_trainer) TrainerConfig (class in alf.algorithms.config) training (ActorCriticAlgorithm attribute) (ActorCriticLoss attribute) (ActorDistributionNetwork attribute) (ActorDistributionNetworkBase attribute) (ActorDistributionRNNNetwork attribute) (ActorNetwork attribute) (ActorNetworkBase attribute) (ActorRNNNetwork attribute) (AdaptiveAverager attribute) (AdaptiveNormalizer attribute) (AddN attribute) (Agent attribute) (Algorithm attribute) (AlgorithmContainer attribute) (AlgorithmInterface attribute) (AMPWrapper attribute), [1] (AsymmetricSimSiamLoss attribute) (AutoShapeImageDeconvNetwork attribute) (AverageDiscountedReturnMetric attribute) (AverageEnvInfoMetric attribute) (AverageEpisodeLengthMetric attribute) (AverageEpisodicAggregationMetric attribute) (AverageReturnMetric attribute) (AverageRewardMetric attribute) (BatchNorm1d attribute) (BatchNorm2d attribute) (BatchSquashNetwork attribute) (BcAlgorithm attribute) (BetaProjectionNetwork attribute) (BottleneckBlock attribute) (Branch attribute) (Cast attribute) (CategoricalProjectionNetwork attribute) (CategoricalSeedSampler attribute) (CauchyProjectionNetwork attribute) (CausalBcAlgorithm attribute) (CausalConv1D attribute) (CEMPlanAlgorithm attribute) (CompositionalFC attribute) (Conv2D attribute) (Conv2DBatchEnsemble attribute) (ConvTranspose2D attribute) (CriticAlgorithm attribute) (CriticNetwork attribute) (CriticRNNNetwork attribute) (DataBuffer attribute) (DataTransformer attribute) (DdpgAlgorithm attribute) (DecodingAlgorithm attribute) (Delay attribute) (Detach attribute) (DeterministicDynamicsAlgorithm attribute) (DIAYNAlgorithm attribute) (DiscreteVAE attribute) (DisjointPolicyValueNetwork attribute) (DqnAlgorithm attribute) (DynamicActionRepeatAgent attribute) (DynamicsLearningAlgorithm attribute) (DynamicsNetwork attribute) (Echo attribute) (EchoAlg attribute) (ElementwiseLayerBase attribute) (EMAverager attribute) (EmbeddingPreprocessor attribute) (EMNormalizer attribute) (EncodingAlgorithm attribute) (EncodingNetwork attribute) (EntropyTargetAlgorithm attribute) (EnvironmentSteps attribute) (EpisodicStartAverageDiscountedReturnMetric attribute) (EpsilonGreedySampler attribute) (FC attribute) (FCBatchEnsemble attribute) (FixedDecodingLayer attribute) (FixedRewardFunction attribute) (FrameStacker attribute) (FuncParVIAlgorithm attribute) (FunctionalRewardTransformer attribute) (Generator attribute) (GetFields attribute) (GFT attribute) (GradientNoiseScaleEstimator attribute) (GRUCell attribute) (HandcraftedAlgorithm attribute) (HindsightExperienceTransformer attribute) (HyperNetwork attribute) (ICMAlgorithm attribute) (Identity attribute) (IdentityDataTransformer attribute) (ImageDecodingNetwork attribute) (ImageDecodingNetworkV2 attribute) (ImageEncodingNetwork attribute) (ImageScaleTransformer attribute) (InverseMVPAlgorithm attribute) (IqlAlgorithm attribute) (LagrangianPredRewardWeightAlgorithm attribute) (LagrangianRewardWeightAlgorithm attribute) (Lambda attribute) (LatentActorDistributionNetwork attribute) (LatentMbrlAlgorithm attribute) (Loss attribute) (LSTMCell attribute) (LSTMEncodingNetwork attribute) (MaxSegmentTree attribute) (MbrlAlgorithm attribute) (MCTSAlgorithm attribute) (MCTSModel attribute) (MdqAlgorithm attribute) (MdqCriticNetwork attribute) (MemoryBasedActor attribute) (MemoryBasedPredictor attribute) (MerlinAlgorithm attribute) (MetricBuffer attribute) (MIEstimator attribute) (MinSegmentTree attribute) (MixtureProjectionNetwork attribute) (MoNetAlgorithm attribute) (MoNetUNet attribute) (MultinomialSampler attribute) (MuzeroAlgorithm attribute) (MuzeroRepresentationImpl attribute) (MuzeroRepresentationLearner attribute) (NaiveParallelLayer attribute) (NaiveParallelNetwork attribute) (NestCombiner attribute) (NestConcat attribute) (NestedEntropyTargetAlgorithm attribute) (NestMultiply attribute) (NestOuterProduct attribute) (NestSum attribute) (Network attribute) (NetworkWrapper attribute) (NoisyFC attribute) (Normalizer attribute) (NormalizingFlowNetwork attribute) (NormalProjectionNetwork attribute) (NumberOfEpisodes attribute) (OacAlgorithm attribute) (ObservationNormalizer attribute) (OffPolicyAlgorithm attribute) (OneHot attribute) (OnehotCategoricalProjectionNetwork attribute) (OneStepTDLoss attribute) (OneStepTDQRLoss attribute) (OnPolicyAlgorithm attribute) (OUProcess attribute), [1] (Parallel attribute) (ParallelActorDistributionNetwork attribute) (ParallelCategoricalProjectionNetwork attribute) (ParallelConv2D attribute) (ParallelConvTranspose2D attribute) (ParallelDynamicsNetwork attribute) (ParallelFC attribute) (ParallelQNetwork attribute) (ParallelValueNetwork attribute) (ParamConv2D attribute) (ParamConvNet attribute) (ParamFC attribute) (ParamLayerNorm attribute) (ParamLayerNorm1d attribute) (ParamLayerNorm2d attribute) (ParamNetwork attribute) (ParVIAlgorithm attribute) (Periodically attribute) (Permute attribute) (PlanAlgorithm attribute) (PPGAlgorithm attribute) (PPGAuxAlgorithm attribute) (PPGAuxPhaseLoss attribute) (PPOAlgorithm attribute) (PPOLoss attribute) (PredictiveRepresentationLearner attribute) (PreprocessorNetwork attribute) (QNetwork attribute) (QNetworkBase attribute) (QRNNNetwork attribute) (QrsacAlgorithm attribute) (RandomCategoricalGoalGenerator attribute) (RandomCrop attribute) (RandomShootingAlgorithm attribute) (RealNVPNetwork attribute) (ReluMLP attribute) (ReplayBuffer attribute) (ReplicationPad2d attribute) (Reshape attribute) (Residue attribute) (ResidueBlock attribute) (ResnetDecodingNetwork attribute) (ResnetEncodingNetwork attribute) (RewardClipping attribute) (RewardEstimationAlgorithm attribute) (RewardNormalizer attribute) (RewardScaling attribute) (RewardShifting attribute) (RewardTransformer attribute) (RingBuffer attribute) (RLAlgorithm attribute) (RLAlgWrapper attribute) (RNDAlgorithm attribute) (SacAlgorithm attribute) (SameActionPriorActor attribute) (SarsaAlgorithm attribute) (ScalarAdaptiveAverager attribute) (ScalarAdaptiveNormalizer attribute) (ScalarEMAverager attribute) (ScalarEMNormalizer attribute) (ScalarWindowAverager attribute) (ScalarWindowNormalizer attribute) (Scale attribute) (ScaleGradient attribute) (SegmentTree attribute) (Sequential attribute) (SequentialDataTransformer attribute) (SGDEntropyTargetAlgorithm attribute) (SimpleActionEncoder attribute) (SimpleAttention attribute) (SimpleCarlaAlgorithm attribute) (SimpleDataTransformer attribute) (SimpleDecoder attribute) (SimpleMCTSModel attribute) (SimplePredictionNet attribute) (SocialAttentionNetwork attribute) (StableNormalProjectionNetwork attribute) (StepMetric attribute) (StochasticDynamicsAlgorithm attribute) (Sum attribute) (SummarizeGradient attribute) (SumSegmentTree attribute) (TaacAlgorithm attribute) (TaacAlgorithmBase attribute) (TaacLAlgorithm attribute) (TaacQAlgorithm attribute) (TAACTDLoss attribute) (TargetUpdater attribute) (TDLoss attribute) (TDQRLoss attribute) (TemporalPool attribute) (TracAlgorithm attribute) (TransformerBlock attribute) (TransformerNetwork attribute) (Transpose attribute) (TruncatedProjectionNetwork attribute) (UniformPriorActor attribute) (UnitNormalActorDistributionNetwork attribute) (UntransformedTimeStep attribute) (ValueNetwork attribute) (ValueNetworkBase attribute) (ValueRNNNetwork attribute) (VariationalAutoEncoder attribute) (Vqvae attribute) (WindowAverager attribute) (WindowNormalizer attribute)

training_worker() (in module alf.bin.train) TrajOptimizer (class in alf.optimizers.traj_optimizers) transform() (InvertibleTransform method) (Log1pTransform method) (Sqrt1pTransform method) (SqrtLinearTransform method) transform_experience() (Algorithm method) (DataTransformer method) (FrameStacker method) (HindsightExperienceTransformer method) (SequentialDataTransformer method) (SimpleDataTransformer method) transform_nest() (in module alf.nest.nest) transform_nests() (in module alf.nest.nest) transform_observation() (BaseObservationWrapper method) (EpisodicRandomFrameCrop method) (FlattenObservation method) (FrameCrop method) (FrameFlip method) (FrameGrayScale method) (FrameResize method) (FrameStack method) (ImageChannelFirst method) transform_space() (BaseObservationWrapper method) (EpisodicRandomFrameCrop method) (FlattenObservation method) (FrameCrop method) (FrameFlip method) (FrameGrayScale method) (FrameResize method) (FrameStack method) (ImageChannelFirst method) (in module alf.environments.gym_wrappers) transform_timestep() (Algorithm method) (DataTransformer method) (FrameStacker method) (HindsightExperienceTransformer method) (SequentialDataTransformer method) (SimpleDataTransformer method) transform_to_geolocation() (World method) transformed() (Polyline method) transformed_observation_spec (DataTransformer property) transformed_within_fov() (Polyline method) TransformerBlock (class in alf.layers) TransformerNetwork (class in alf.networks.transformer_networks) transition() (in module alf.data_structures) Transpose (class in alf.layers) transpose() (in module alf.nest.nest) TruncatedCauchy (class in alf.utils.distributions) TruncatedDistribution (class in alf.utils.distributions) TruncatedNormal (class in alf.algorithms.prior_actor) (class in alf.utils.distributions) TruncatedProjectionNetwork (class in alf.networks.projection_networks) TruncatedT2 (class in alf.utils.distributions) TrustedUpdater (class in alf.optimizers.trusted_updater) tuplify2d() (in module alf.utils.common) type (EvalJob attribute) (NumpyLaneMarking attribute) (UnrollJob attribute)

U

u (Tau attribute) unbatch_nested_tensor() (in module alf.nest.nest) unflatten() (BatchSquash method) UniformPriorActor (class in alf.algorithms.prior_actor) UnitNormalActorDistributionNetwork (class in alf.networks.actor_distribution_networks) UnittestEnv (class in alf.environments.suite_unittest) unroll() (RLAlgorithm method) UnrollJob (class in alf.algorithms.async_unroller) UnrollResult (class in alf.algorithms.async_unroller) UntransformedTimeStep (class in alf.algorithms.data_transformer) UnwrappedEnvChecker (class in alf.environments.utils) unzip_alf_snapshot() (in module alf.utils.common) update() (AdaptiveAverager method) (EMAverager method) (GoBoard method) (Normalizer method) (UnwrappedEnvChecker method) (WindowAverager method)

update_actor_location() (World method) update_parameter() (AsyncUnroller method) update_priority() (ReplayBuffer method) update_speed_limit() (Player method) update_state() (DeterministicDynamicsAlgorithm method) (DynamicsLearningAlgorithm method) update_time_step_field() (Experience method) update_with_gradient() (Algorithm method) upper_bound (TruncatedDistribution property) usage (MemoryWithUsage property) use_conditional_inputs (NormalizingFlowNetwork property) use_gpu (GridSearchConfig property) use_rollout_state (Algorithm property)

V

v (Tau attribute) vae (MBPLossInfo attribute) VAEInfo (class in alf.algorithms.vae) VAEOutput (class in alf.algorithms.vae) validate_pre_configs() (in module alf.config_util) value (ActorCriticInfo attribute) (ActorCriticState attribute) (IqlCriticInfo attribute) (MCTSInfo attribute) (ModelOutput attribute) (ModelTarget attribute) (MuzeroInfo attribute) (PPGRolloutInfo attribute) (PPOInfo attribute) value_loss (TaacActorInfo attribute) (TaacCriticInfo attribute) value_pred (ModelOutput attribute)

ValueNetwork (class in alf.networks.value_networks) ValueNetworkBase (class in alf.networks.value_networks) ValueRNNNetwork (class in alf.networks.value_networks) ValueUnittestEnv (class in alf.environments.suite_unittest) variance (AffineTransformedDistribution property) variance_scaling_init() (in module alf.initializers) VariationalAutoEncoder (class in alf.algorithms.vae) VectorizedObservation (class in alf.environments.metadrive.sensors) VectorizedTopDownEnv (class in alf.environments.metadrive.environments) VehicleController (class in alf.environments.carla_controller) vehicles_with_functioning_lights (CarlaEnvironment attribute) VideoRecorder (class in alf.utils.video_recorder) VisitSoftmaxTemperatureByMoves (class in alf.algorithms.mcts_algorithm) VisitSoftmaxTemperatureByProgress (class in alf.algorithms.mcts_algorithm) VOCAB (BabyAIWrapper attribute) VOCAB_SIZE (BabyAIWrapper attribute) Vqvae (class in alf.algorithms.vq_vae) VqvaeLossInfo (class in alf.algorithms.vq_vae)

W

wait_for_stop() (Coordinator method) wait_start() (ProcessEnvironment method) warning() (in module alf.utils.common) warning_once() (in module alf.utils.common) WeatherParameters (class in alf.environments.suite_carla) weight (CausalConv1D property) (CompositionalFC property) (Conv2D property) (ConvTranspose2D property) (FC property) (FixedDecodingLayer property) (NoisyFC property) (ParallelConv2D property) (ParallelConvTranspose2D property) (ParallelFC property) (ParamConv2D property) (ParamFC property) (ParamLayerNorm property) (SimpleFC attribute) weight_length (ParamConv2D property) (ParamFC property) (ParamLayerNorm property)

weighted_reduce_mean() (in module alf.utils.math_ops) width (NumpyLaneMarking attribute) WINDOW (NavigationSensor attribute) WindowAverager (class in alf.utils.averager) WindowNormalizer (class in alf.utils.normalizers) with_cache() (Softclip method) (Softplus method) (Softsign method) (StableTanh method) within() (FieldOfView method) World (class in alf.environments.carla_sensors) world_polyline_to_ego_array() (DynamicObjectSensor method) wrap_as_network() (in module alf.networks.network) wrap_env() (in module alf.environments.suite_gym) wrap_optimizer() (in module alf.optimizers.optimizers) wrapped_env() (AlfEnvironmentBaseWrapper method) write() (FIFOMemory method) (Memory method) (MemoryWithUsage method) write_config() (in module alf.utils.common) write_gin_configs() (in module alf.utils.common)

X

x_label (EnvironmentStepsReturnReader property) (EnvironmentStepsSuccessReader property) (IterationsReturnReader property) (IterationsSuccessReader property) (MeanCurveGroupReader property) (MeanCurveReader property)

Y

y_label (EnvironmentStepsReturnReader property) (EnvironmentStepsSuccessReader property) (IterationsReturnReader property) (IterationsSuccessReader property) (MeanCurveGroupReader property) (MeanCurveReader property)

Z

z (VAEOutput attribute) z_dist (MoNetInfo attribute) z_mode (VAEOutput attribute) z_std (VAEInfo attribute) (VAEOutput attribute)

zeros() (TensorSpec method) zeros_from_spec() (in module alf.utils.spec_utils) zeros_like() (in module alf.nest.utils)