Index _ | A | B | C | D | E | F | G | I | L | M | N | O | P | Q | R | S | T | U | V | W _ __check_algo_configs() (in module omnisafe.utils.config) __check_logger_configs() (in module omnisafe.utils.config) __init__() (omnisafe.algorithms.on_policy.CPO method) (omnisafe.algorithms.on_policy.CUP method) (omnisafe.algorithms.on_policy.FOCOPS method) (omnisafe.algorithms.on_policy.IPO method) (omnisafe.algorithms.on_policy.NaturalPG method) (omnisafe.algorithms.on_policy.OnCRPO method) (omnisafe.algorithms.on_policy.P3O method) (omnisafe.algorithms.on_policy.PCPO method) (omnisafe.algorithms.on_policy.PolicyGradient method) (omnisafe.algorithms.on_policy.PPO method) (omnisafe.algorithms.on_policy.PPOLag method) (omnisafe.algorithms.on_policy.TRPO method) (omnisafe.algorithms.on_policy.TRPOLag method) (omnisafe.common.buffer.BaseBuffer method) (omnisafe.common.buffer.OffPolicyBuffer method) (omnisafe.common.buffer.OnPolicyBuffer method) (omnisafe.common.buffer.VectorOffPolicyBuffer method) (omnisafe.common.buffer.VectorOnPolicyBuffer method) (omnisafe.common.experiment_grid.ExperimentGrid method) (omnisafe.common.lagrange.Lagrange method) (omnisafe.common.logger.Logger method) (omnisafe.common.normalizer.Normalizer method) (omnisafe.common.pid_lagrange.PIDLagrangian method) (omnisafe.models.actor.ActorBuilder method) (omnisafe.models.actor.GaussianActor method) (omnisafe.models.actor.GaussianLearningActor method) (omnisafe.models.actor.GaussianSACActor method) (omnisafe.models.base.Actor method) (omnisafe.utils.config.Config method) (omnisafe.utils.config.ModelConfig method) _calculate_adv_and_value_targets() (omnisafe.common.buffer.OnPolicyBuffer method) _calculate_v_trace() (omnisafe.common.buffer.OnPolicyBuffer static method) _call() (omnisafe.utils.math.SafeTanhTransformer method) _compute_adv_surrogate() (omnisafe.algorithms.on_policy.FOCOPS method) (omnisafe.algorithms.on_policy.IPO method) (omnisafe.algorithms.on_policy.OnCRPO method) (omnisafe.algorithms.on_policy.PolicyGradient method) (omnisafe.algorithms.on_policy.PPOLag method) (omnisafe.algorithms.on_policy.TRPOLag method) _cpo_search_step() (omnisafe.algorithms.on_policy.CPO method) _default_shorthand() (omnisafe.common.experiment_grid.ExperimentGrid method) _distribution() (omnisafe.models.actor.GaussianLearningActor method) (omnisafe.models.actor.GaussianSACActor method) (omnisafe.models.base.Actor method) _fvp() (omnisafe.algorithms.on_policy.NaturalPG method) _init() (omnisafe.algorithms.on_policy.CUP method) (omnisafe.algorithms.on_policy.FOCOPS method) (omnisafe.algorithms.on_policy.PolicyGradient method) (omnisafe.algorithms.on_policy.PPOLag method) (omnisafe.algorithms.on_policy.TRPOLag method) _init_env() (omnisafe.algorithms.on_policy.PolicyGradient method) _init_log() (omnisafe.algorithms.on_policy.CPO method) (omnisafe.algorithms.on_policy.CUP method) (omnisafe.algorithms.on_policy.FOCOPS method) (omnisafe.algorithms.on_policy.IPO method) (omnisafe.algorithms.on_policy.NaturalPG method) (omnisafe.algorithms.on_policy.OnCRPO method) (omnisafe.algorithms.on_policy.P3O method) (omnisafe.algorithms.on_policy.PolicyGradient method) (omnisafe.algorithms.on_policy.PPOLag method) (omnisafe.algorithms.on_policy.TRPO method) (omnisafe.algorithms.on_policy.TRPOLag method) _init_model() (omnisafe.algorithms.on_policy.PolicyGradient method) _inverse() (omnisafe.utils.math.SafeTanhTransformer method) _loss_pi() (omnisafe.algorithms.on_policy.FOCOPS method) (omnisafe.algorithms.on_policy.PolicyGradient method) (omnisafe.algorithms.on_policy.PPO method) _loss_pi_cost() (omnisafe.algorithms.on_policy.CPO method) (omnisafe.algorithms.on_policy.CUP method) (omnisafe.algorithms.on_policy.P3O method) _push() (omnisafe.common.normalizer.Normalizer method) _search_step_size() (omnisafe.algorithms.on_policy.TRPO method) _update() (omnisafe.algorithms.on_policy.CUP method) (omnisafe.algorithms.on_policy.FOCOPS method) (omnisafe.algorithms.on_policy.NaturalPG method) (omnisafe.algorithms.on_policy.PolicyGradient method) (omnisafe.algorithms.on_policy.PPOLag method) (omnisafe.algorithms.on_policy.TRPOLag method) _update_actor() (omnisafe.algorithms.on_policy.CPO method) (omnisafe.algorithms.on_policy.NaturalPG method) (omnisafe.algorithms.on_policy.P3O method) (omnisafe.algorithms.on_policy.PCPO method) (omnisafe.algorithms.on_policy.PolicyGradient method) (omnisafe.algorithms.on_policy.TRPO method) _update_cost_critic() (omnisafe.algorithms.on_policy.PolicyGradient method) _update_current_row() (omnisafe.common.logger.Logger method) _update_reward_critic() (omnisafe.algorithms.on_policy.PolicyGradient method) _variants() (omnisafe.common.experiment_grid.ExperimentGrid method) A Actor (class in omnisafe.models.base) ActorBuilder (class in omnisafe.models.actor) add() (omnisafe.common.experiment_grid.ExperimentGrid method) add_field() (omnisafe.common.buffer.BaseBuffer method) (omnisafe.common.buffer.VectorOffPolicyBuffer method) all_bools() (in module omnisafe.utils.exp_grid_tools) avg_grads() (in module omnisafe.utils.distributed) avg_params() (in module omnisafe.utils.distributed) avg_tensor() (in module omnisafe.utils.distributed) B BaseBuffer (class in omnisafe.common.buffer) batch_size (omnisafe.common.buffer.OffPolicyBuffer property) build_actor() (omnisafe.models.actor.ActorBuilder method) build_critic() (omnisafe.models.critic.CriticBuilder method) build_mlp_network() (in module omnisafe.utils.model) C check_all_configs() (in module omnisafe.utils.config) check_variant_vaild() (omnisafe.common.experiment_grid.ExperimentGrid method) close() (omnisafe.common.logger.Logger method) compute_lambda_loss() (omnisafe.common.lagrange.Lagrange method) Config (class in omnisafe.utils.config) conjugate_gradients() (in module omnisafe.utils.math) CPO (class in omnisafe.algorithms.on_policy) Critic (class in omnisafe.models.base) CriticBuilder (class in omnisafe.models.critic) CUP (class in omnisafe.algorithms.on_policy) current_epoch (omnisafe.common.logger.Logger property) custom_cfgs_to_dict() (in module omnisafe.utils.tools) D device (omnisafe.common.buffer.BaseBuffer property) dict2config() (omnisafe.utils.config.Config static method) discount_cumsum() (in module omnisafe.utils.math) dist_avg() (in module omnisafe.utils.distributed) dist_max() (in module omnisafe.utils.distributed) dist_min() (in module omnisafe.utils.distributed) dist_op() (in module omnisafe.utils.distributed) dist_statistics_scalar() (in module omnisafe.utils.distributed) dist_sum() (in module omnisafe.utils.distributed) dump_tabular() (omnisafe.common.logger.Logger method) E entropy() (omnisafe.utils.math.TanhNormal method) expand() (omnisafe.utils.math.TanhNormal method) ExperimentGrid (class in omnisafe.common.experiment_grid) F finish_path() (omnisafe.common.buffer.OnPolicyBuffer method) (omnisafe.common.buffer.VectorOnPolicyBuffer method) FOCOPS (class in omnisafe.algorithms.on_policy) fork() (in module omnisafe.utils.distributed) forward() (omnisafe.common.normalizer.Normalizer method) (omnisafe.models.actor.GaussianLearningActor method) (omnisafe.models.actor.GaussianSACActor method) (omnisafe.models.base.Actor method) (omnisafe.models.critic.QCritic method) (omnisafe.models.critic.VCritic method) G gaussian_kl() (in module omnisafe.utils.math) GaussianActor (class in omnisafe.models.actor) GaussianLearningActor (class in omnisafe.models.actor) GaussianSACActor (class in omnisafe.models.actor) get() (omnisafe.common.buffer.OnPolicyBuffer method) (omnisafe.common.buffer.VectorOnPolicyBuffer method) get_activation() (in module omnisafe.utils.model) get_default_kwargs_yaml() (in module omnisafe.utils.config) get_diagonal() (in module omnisafe.utils.math) get_flat_gradients_from() (in module omnisafe.utils.tools) get_flat_params_from() (in module omnisafe.utils.tools) get_rank() (in module omnisafe.utils.distributed) get_stats() (omnisafe.common.logger.Logger method) get_transpose() (in module omnisafe.utils.math) I initialize_layer() (in module omnisafe.utils.model) IPO (class in omnisafe.algorithms.on_policy) is_master() (in module omnisafe.utils.distributed) L Lagrange (class in omnisafe.common.lagrange) learn() (omnisafe.algorithms.on_policy.PolicyGradient method) load_state_dict() (omnisafe.common.normalizer.Normalizer method) load_yaml() (in module omnisafe.utils.tools) loc (omnisafe.utils.math.TanhNormal property) log() (omnisafe.common.logger.Logger method) log_prob() (omnisafe.models.actor.GaussianLearningActor method) (omnisafe.models.actor.GaussianSACActor method) (omnisafe.models.base.Actor method) Logger (class in omnisafe.common.logger) M max_size (omnisafe.common.buffer.OffPolicyBuffer property) mean (omnisafe.common.normalizer.Normalizer property) (omnisafe.utils.math.TanhNormal property) ModelConfig (class in omnisafe.utils.config) N NaturalPG (class in omnisafe.algorithms.on_policy) normalize() (omnisafe.common.normalizer.Normalizer method) Normalizer (class in omnisafe.common.normalizer) num_buffers (omnisafe.common.buffer.VectorOnPolicyBuffer property) num_envs (omnisafe.common.buffer.VectorOffPolicyBuffer property) O OffPolicyBuffer (class in omnisafe.common.buffer) OnCRPO (class in omnisafe.algorithms.on_policy) OnPolicyBuffer (class in omnisafe.common.buffer) P P3O (class in omnisafe.algorithms.on_policy) PCPO (class in omnisafe.algorithms.on_policy) pid_update() (omnisafe.common.pid_lagrange.PIDLagrangian method) PIDLagrangian (class in omnisafe.common.pid_lagrange) PolicyGradient (class in omnisafe.algorithms.on_policy) PPO (class in omnisafe.algorithms.on_policy) PPOLag (class in omnisafe.algorithms.on_policy) predict() (omnisafe.models.actor.GaussianLearningActor method) (omnisafe.models.actor.GaussianSACActor method) (omnisafe.models.base.Actor method) print() (omnisafe.common.experiment_grid.ExperimentGrid method) Q QCritic (class in omnisafe.models.critic) R recurisve_update() (omnisafe.utils.config.Config method) recursive_check_config() (in module omnisafe.utils.tools) register_key() (omnisafe.common.logger.Logger method) run() (omnisafe.common.experiment_grid.ExperimentGrid method) S safe_inverse() (in module omnisafe.utils.math) SafeTanhTransformer (class in omnisafe.utils.math) sample_batch() (omnisafe.common.buffer.OffPolicyBuffer method) (omnisafe.common.buffer.VectorOffPolicyBuffer method) save_config() (omnisafe.common.logger.Logger method) save_grid_config() (omnisafe.common.experiment_grid.ExperimentGrid method) save_results() (omnisafe.common.experiment_grid.ExperimentGrid method) save_same_exps_config() (omnisafe.common.experiment_grid.ExperimentGrid method) scale (omnisafe.utils.math.TanhNormal property) seed_all() (in module omnisafe.utils.tools) set_optimizer() (in module omnisafe.utils.model) set_param_values_to_model() (in module omnisafe.utils.tools) setup_distributed() (in module omnisafe.utils.distributed) setup_torch_saver() (omnisafe.common.logger.Logger method) shape (omnisafe.common.normalizer.Normalizer property) size (omnisafe.common.buffer.BaseBuffer property) standardized_adv_c (omnisafe.common.buffer.OnPolicyBuffer property) standardized_adv_r (omnisafe.common.buffer.OnPolicyBuffer property) std (omnisafe.common.normalizer.Normalizer property) (omnisafe.models.actor.GaussianActor property) (omnisafe.models.actor.GaussianLearningActor property) (omnisafe.models.actor.GaussianSACActor property) stddev (omnisafe.utils.math.TanhNormal property) store() (omnisafe.common.buffer.BaseBuffer method) (omnisafe.common.buffer.OffPolicyBuffer method) (omnisafe.common.buffer.OnPolicyBuffer method) (omnisafe.common.buffer.VectorOnPolicyBuffer method) (omnisafe.common.logger.Logger method) sync_params() (in module omnisafe.utils.distributed) T TanhNormal (class in omnisafe.utils.math) todict() (omnisafe.utils.config.Config method) tojson() (omnisafe.utils.config.Config method) torch_save() (omnisafe.common.logger.Logger method) TRPO (class in omnisafe.algorithms.on_policy) TRPOLag (class in omnisafe.algorithms.on_policy) U update_dic() (in module omnisafe.utils.tools) (omnisafe.common.experiment_grid.ExperimentGrid method) update_lagrange_multiplier() (omnisafe.common.lagrange.Lagrange method) V valid_str() (in module omnisafe.utils.exp_grid_tools) variance (omnisafe.utils.math.TanhNormal property) variant_name() (omnisafe.common.experiment_grid.ExperimentGrid method) variants() (omnisafe.common.experiment_grid.ExperimentGrid method) VCritic (class in omnisafe.models.critic) VectorOffPolicyBuffer (class in omnisafe.common.buffer) VectorOnPolicyBuffer (class in omnisafe.common.buffer) W world_size() (in module omnisafe.utils.distributed)