Index

A

act() (mbrl.planning.Agent method) (mbrl.planning.RandomAgent method) (mbrl.planning.TrajectoryOptimizerAgent method)

add() (mbrl.util.replay_buffer.ReplayBuffer method) Agent (class in mbrl.planning)

B

BasicEnsemble (class in mbrl.models)

BootstrapIterator (class in mbrl.util.replay_buffer)

C

CEMOptimizer (class in mbrl.planning) complete_agent_cfg() (in module mbrl.planning)

create_one_dim_tr_model() (in module mbrl.util.common) create_replay_buffer() (in module mbrl.util.common) create_trajectory_optim_agent_for_model() (in module mbrl.planning)

D

denormalize() (mbrl.util.math.Normalizer method)

E

Ensemble (class in mbrl.models) EnsembleLinearLayer (class in mbrl.models) eval_score() (mbrl.models.BasicEnsemble method) (mbrl.models.Ensemble method) (mbrl.models.GaussianMLP method) (mbrl.models.Model method) (mbrl.models.OneDTransitionRewardModel method)

evaluate() (mbrl.models.ModelTrainer method) evaluate_action_sequences() (mbrl.models.ModelEnv method) extra_repr() (mbrl.models.EnsembleLinearLayer method)

F

forward() (mbrl.models.BasicEnsemble method) (mbrl.models.Ensemble method) (mbrl.models.EnsembleLinearLayer method) (mbrl.models.GaussianMLP method) (mbrl.models.Model method) (mbrl.models.OneDTransitionRewardModel method)

freeze_mujoco_env (class in mbrl.util.mujoco)

G

gaussian_nll() (in module mbrl.util.math) GaussianMLP (class in mbrl.models) get_all() (mbrl.util.replay_buffer.ReplayBuffer method)

get_current_state() (in module mbrl.util.mujoco) get_iterators() (mbrl.util.replay_buffer.ReplayBuffer method) get_output_and_targets() (mbrl.models.OneDTransitionRewardModel method)

L

load() (mbrl.models.Model method) (mbrl.models.OneDTransitionRewardModel method) (mbrl.util.math.Normalizer method) (mbrl.util.replay_buffer.ReplayBuffer method) load_agent() (in module mbrl.planning) load_hydra_cfg() (in module mbrl.util.common)

log_data() (mbrl.util.logger.Logger method) Logger (class in mbrl.util.logger) loss() (mbrl.models.BasicEnsemble method) (mbrl.models.Ensemble method) (mbrl.models.GaussianMLP method) (mbrl.models.Model method) (mbrl.models.OneDTransitionRewardModel method)

M

make_env() (in module mbrl.util.mujoco) make_env_from_str() (in module mbrl.util.mujoco) maybe_get_best_weights() (mbrl.models.ModelTrainer method) mbrl.models module mbrl.planning module mbrl.util.common module mbrl.util.logger module mbrl.util.math module mbrl.util.mujoco module

mbrl.util.replay_buffer module Model (class in mbrl.models) ModelEnv (class in mbrl.models) ModelTrainer (class in mbrl.models) module mbrl.models mbrl.planning mbrl.util.common mbrl.util.logger mbrl.util.math mbrl.util.mujoco mbrl.util.replay_buffer

N

normalize() (mbrl.util.math.Normalizer method)

Normalizer (class in mbrl.util.math)

O

OneDTransitionRewardModel (class in mbrl.models)

optimize() (mbrl.planning.CEMOptimizer method) (mbrl.planning.TrajectoryOptimizer method)

P

plan() (mbrl.planning.Agent method) (mbrl.planning.TrajectoryOptimizerAgent method) propagate() (in module mbrl.util.math)

propagate_expectation() (in module mbrl.util.math) propagate_fixed_model() (in module mbrl.util.math) propagate_from_indices() (in module mbrl.util.math) propagate_random_model() (in module mbrl.util.math)

R

RandomAgent (class in mbrl.planning) register_group() (mbrl.util.logger.Logger method) ReplayBuffer (class in mbrl.util.replay_buffer) reset() (mbrl.models.BasicEnsemble method) (mbrl.models.GaussianMLP method) (mbrl.models.Model method) (mbrl.models.ModelEnv method) (mbrl.models.OneDTransitionRewardModel method) (mbrl.planning.Agent method) (mbrl.planning.TrajectoryOptimizer method) (mbrl.planning.TrajectoryOptimizerAgent method)

rollout_agent_trajectories() (in module mbrl.util.common) rollout_model_env() (in module mbrl.util.common) rollout_mujoco_env() (in module mbrl.util.mujoco)

S

sample() (mbrl.models.Ensemble method) (mbrl.models.Model method) (mbrl.models.OneDTransitionRewardModel method) (mbrl.util.replay_buffer.ReplayBuffer method) sample_trajectory() (mbrl.util.replay_buffer.ReplayBuffer method) save() (mbrl.models.Model method) (mbrl.models.OneDTransitionRewardModel method) (mbrl.util.math.Normalizer method) (mbrl.util.replay_buffer.ReplayBuffer method)

set_elite() (mbrl.models.BasicEnsemble method) (mbrl.models.Ensemble method) (mbrl.models.GaussianMLP method) set_env_state() (in module mbrl.util.mujoco) set_trajectory_eval_fn() (mbrl.planning.TrajectoryOptimizerAgent method) step() (mbrl.models.ModelEnv method) step_env_and_add_to_buffer() (in module mbrl.util.common)

T

toggle_bootstrap() (mbrl.util.replay_buffer.BootstrapIterator method) train() (mbrl.models.ModelTrainer method) train_model_and_save_model_and_data() (in module mbrl.util.common) TrajectoryOptimizer (class in mbrl.planning)

TrajectoryOptimizerAgent (class in mbrl.planning) TransitionIterator (class in mbrl.util.replay_buffer) truncated_linear() (in module mbrl.util.math) truncated_normal_() (in module mbrl.util.math) truncated_normal_init() (in module mbrl.models)

U

update() (mbrl.models.Model method) (mbrl.models.OneDTransitionRewardModel method)

update_normalizer() (mbrl.models.OneDTransitionRewardModel method) update_stats() (mbrl.util.math.Normalizer method)