Index

_

__call__() (PyTorchPolicy method) (Reward method)

_get_dict() (Registrable method) _make_from_dict() (Registrable class method)

A

accept_info() (in module navground.learning.types) action (GroupConfig attribute) Action (in module navground.learning.types) action_config() (MultiAgentNavgroundEnv method) (NavgroundEnv method) action_size (ControlActionConfig property) action_space (BaseILAlgorithm property) (OnnxPolicy property) action_space() (NavgroundExperiment method) ActionConfig (class in navground.learning.config) ActorSpec (in module navground.learning.policies.split_sac_policy) actuate() (GroupedPolicyBehavior method) (PolicyBehavior method) actuated_twist (GroupedPolicyBehavior property) (PolicyBehavior property) actuated_wheel_speeds (GroupedPolicyBehavior property) (PolicyBehavior property) add_modulation() (GroupedPolicyBehavior method) (PolicyBehavior method)

all() (Indices class method) AlternateActorCallback (class in navground.learning.policies.split_sac_policy) (class in navground.learning.utils.benchmarl) angular_speed (GroupedPolicyBehavior property) (PolicyBehavior property) AnyPolicy (in module navground.learning.il) AnyPolicyPredictor (in module navground.learning.types) Array (in module navground.learning.types) as_set() (Indices method) asdict (ControlActionConfig property) (DefaultObservationConfig property) (DefaultStateConfig property) (GroupConfig property) (Indices property) (MultiAgentNavgroundEnv property) (NavgroundEnv property) (Registrable property) assume_cmd_is_actuated (GroupedPolicyBehavior property) (PolicyBehavior property)

B

BaseEnv (in module navground.learning.env) BaseILAlgorithm (class in navground.learning.il) BaseParallelEnv (in module navground.learning.parallel_env)

BC (class in navground.learning.il) BinaryControlActionConfig (class in navground.learning.config) Bounds (in module navground.learning.types)

C

CentralizedPadBehavior (class in navground.learning.behaviors.pad) check_if_target_satisfied() (GroupedPolicyBehavior method) (PolicyBehavior method) clear_modulations() (GroupedPolicyBehavior method) (PolicyBehavior method) clone() (GroupedPolicyBehavior method) (PolicyBehavior method) clone_behavior() (GroupedPolicyBehavior class method) (PolicyBehavior class method) close() (PolicyBehavior method) cmd_twist_along_path() (GroupedPolicyBehavior method) (PolicyBehavior method) cmd_twist_towards_angular_speed() (GroupedPolicyBehavior method) (PolicyBehavior method) cmd_twist_towards_orientation() (GroupedPolicyBehavior method) (PolicyBehavior method) cmd_twist_towards_point() (GroupedPolicyBehavior method) (PolicyBehavior method) cmd_twist_towards_pose() (GroupedPolicyBehavior method) (PolicyBehavior method) cmd_twist_towards_stopping() (GroupedPolicyBehavior method) (PolicyBehavior method)

cmd_twist_towards_velocity() (GroupedPolicyBehavior method) (PolicyBehavior method) collect_runs() (BC method) color (GroupConfig attribute) comm() (in module navground.learning.examples.pad) comm_size (ControlActionWithCommConfig attribute) (DiscreteControlActionWithCommConfig attribute) comm_space (ControlActionWithCommConfig property) (DiscreteControlActionWithCommConfig property) CommProbe (class in navground.learning.probes) CommSensor (class in navground.learning.state_estimations) compute_cmd() (GroupedPolicyBehavior method) (PolicyBehavior method) compute_cmd_internal() (GroupedPolicyBehavior method) config_eval_log() (in module navground.learning.evaluation) configure() (ActionConfig method) (ObservationConfig method) configure_kinematics() (ControlActionConfig method) (DefaultObservationConfig method) ControlActionConfig (class in navground.learning.config) ControlActionWithCommConfig (class in navground.learning.config) CorridorWithObstacle (class in navground.learning.scenarios)

D

DAgger (class in navground.learning.il) DefaultObservationConfig (class in navground.learning.config) DefaultStateConfig (class in navground.learning.config) desired_velocity (GroupedPolicyBehavior property) (PolicyBehavior property) desired_velocity_towards_point() (GroupedPolicyBehavior method) (PolicyBehavior method) desired_velocity_towards_velocity() (GroupedPolicyBehavior method) (PolicyBehavior method) deterministic (GroupConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property)

DiscreteControlActionConfig (class in navground.learning.config) DiscreteControlActionWithCommConfig (class in navground.learning.config) display_episode_video() (in module navground.learning.evaluation) display_run_video() (in module navground.learning.evaluation) DistributedCommPolicy (class in navground.learning.policies.centralized_policy_with_comm) DistributedPadBehavior (class in navground.learning.behaviors.pad) dtype (CommProbe attribute) (RewardProbe attribute) (SuccessProbe attribute) dump() (GroupedPolicyBehavior method) (PolicyBehavior method)

E

efficacy (GroupedPolicyBehavior property) (PolicyBehavior property) EfficacyReward (class in navground.learning.rewards) env (BaseILAlgorithm property) environment_state (GroupedPolicyBehavior property) (PolicyBehavior property) EpisodeStart (in module navground.learning.types) estimate_time_until_target_satisfied() (GroupedPolicyBehavior method) (PolicyBehavior method) evaluate() (in module navground.learning.evaluation) evaluate_policies() (in module navground.learning.evaluation)

evaluate_policy() (in module navground.learning.evaluation) (in module navground.learning.utils.benchmarl) (NavgroundExperiment method) evaluate_with_experiment() (in module navground.learning.evaluation) evaluate_with_experiment_and_env() (in module navground.learning.evaluation) export() (in module navground.learning.onnx) export_behavior() (in module navground.learning.io) export_policies() (NavgroundExperiment method) export_policy() (NavgroundExperiment method) export_policy_as_behavior() (in module navground.learning.io) ExportOnnxCallback (class in navground.learning.utils.sb3) ExportPolicyCallback (class in navground.learning.utils.benchmarl)

F

failure_condition (GroupConfig attribute) feasible_angular_speed() (GroupedPolicyBehavior method) (PolicyBehavior method) feasible_speed() (GroupedPolicyBehavior method) (PolicyBehavior method) feasible_twist() (GroupedPolicyBehavior method) (PolicyBehavior method) feasible_twist_from_current() (GroupedPolicyBehavior method) (PolicyBehavior method) fix_orientation (ControlActionConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property) FixedReward (class in navground.learning.rewards)

flat (DefaultObservationConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property) flat_values (DefaultObservationConfig attribute) forward() (PyTorchPolicy method) ForwardScenario (class in navground.learning.scenarios) from_dict() (ControlActionConfig class method) (DefaultObservationConfig class method) (DefaultStateConfig class method) (Indices class method) (ModulationActionConfig class method) (MultiAgentNavgroundEnv class method) (NavgroundEnv class method) (Registrable class method)

G

generate_trajectories() (in module navground.learning.il.rollout) get() (GroupedPolicyBehavior method) (PolicyBehavior method) get_action() (ActionConfig method) get_actuated_twist() (GroupedPolicyBehavior method) (PolicyBehavior method) get_cmd_from_action() (ActionConfig method) (MultiAgentNavgroundEnv method) (NavgroundEnv method) get_env() (BaseILAlgorithm method) (in module navground.learning.examples.corridor_with_obstacle) (in module navground.learning.examples.cross) (in module navground.learning.examples.pad) get_indices() (NavgroundExperiment method) get_policy() (MultiAgentNavgroundEnv method) get_property_type_name() (GroupedPolicyBehavior method) (PolicyBehavior method) get_single_agent_policies() (NavgroundExperiment method) get_single_agent_policy() (NavgroundExperiment method) get_space() (StateConfig method) get_state() (StateConfig method) get_target_angular_direction() (GroupedPolicyBehavior method) (PolicyBehavior method) get_target_angular_distance() (GroupedPolicyBehavior method) (PolicyBehavior method) get_target_angular_speed() (GroupedPolicyBehavior method) (PolicyBehavior method)

get_target_angular_velocity() (GroupedPolicyBehavior method) (PolicyBehavior method) get_target_direction() (GroupedPolicyBehavior method) (PolicyBehavior method) get_target_distance() (GroupedPolicyBehavior method) (PolicyBehavior method) get_target_orientation() (GroupedPolicyBehavior method) (PolicyBehavior method) get_target_pose() (GroupedPolicyBehavior method) (PolicyBehavior method) get_target_position() (GroupedPolicyBehavior method) (PolicyBehavior method) get_target_speed() (GroupedPolicyBehavior method) (PolicyBehavior method) get_target_twist() (GroupedPolicyBehavior method) (PolicyBehavior method) get_target_velocity() (GroupedPolicyBehavior method) (PolicyBehavior method) get_twist() (GroupedPolicyBehavior method) (PolicyBehavior method) get_velocity() (GroupedPolicyBehavior method) (PolicyBehavior method) GroupConfig (class in navground.learning.config) GroupedPolicyBehavior (class in navground.learning.behaviors) GroupedPolicyBehavior.Heading (class in navground.learning.behaviors) GymProbe (class in navground.learning.probes)

H

has() (GroupedPolicyBehavior method) (PolicyBehavior method) has_target (GroupedPolicyBehavior property) (PolicyBehavior property) has_type() (GroupedPolicyBehavior static method) (PolicyBehavior static method) has_wheels (ControlActionConfig attribute)

heading_behavior (GroupedPolicyBehavior property) (PolicyBehavior property) history (DefaultObservationConfig attribute) (GroupedPolicyBehavior property) (ObservationConfig property) (PolicyBehavior property) horizon (GroupedPolicyBehavior property) (PolicyBehavior property)

I

ignore_keys (DefaultObservationConfig attribute) include_all (DefaultStateConfig attribute) include_angular_speed (DefaultObservationConfig attribute) (DefaultStateConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property) include_orientation (DefaultObservationConfig attribute) (DefaultStateConfig attribute) include_position (DefaultObservationConfig attribute) (DefaultStateConfig attribute) include_radius (DefaultObservationConfig attribute) (DefaultStateConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property) include_target_angular_speed (DefaultObservationConfig attribute) (DefaultStateConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property) include_target_direction (DefaultObservationConfig attribute) (DefaultStateConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property) include_target_direction_validity (DefaultObservationConfig attribute) (DefaultStateConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property) include_target_distance (DefaultObservationConfig attribute) (DefaultStateConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property) include_target_distance_validity (DefaultObservationConfig attribute) (DefaultStateConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property)

include_target_orientation (DefaultObservationConfig attribute) (DefaultStateConfig attribute) include_target_orientation_validity (DefaultObservationConfig attribute) (DefaultStateConfig attribute) include_target_speed (DefaultObservationConfig attribute) (DefaultStateConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property) include_velocity (DefaultObservationConfig attribute) (DefaultStateConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property) include_x (DefaultStateConfig attribute) include_y (DefaultStateConfig attribute) Indices (class in navground.learning.indices) indices (GroupConfig attribute) IndicesLike (in module navground.learning.indices) Info (in module navground.learning.types) InfoPolicy (class in navground.learning.policies.info_predictor) init_args (MultiAgentNavgroundEnv property) (NavgroundEnv property) init_policy() (GroupedPolicyBehavior method) (PolicyBehavior method) init_world() (CorridorWithObstacle method) (ForwardScenario method) InitPolicyBehavior (class in navground.learning.evaluation) InputSpec (in module navground.learning.policies.split_sac_policy) intersect() (Indices method) is_configured() (ActionConfig method) (ObservationConfig method) is_stopped() (GroupedPolicyBehavior method) (PolicyBehavior method) is_stuck (GroupedPolicyBehavior property) (PolicyBehavior property)

J

join_indices() (in module navground.learning.indices)

JointEnv (class in navground.learning.parallel_env)

K

keys (DefaultObservationConfig attribute)

kinematics (GroupedPolicyBehavior property) (PolicyBehavior property)

L

learn() (BaseILAlgorithm method) length (CorridorWithObstacle property) load() (BaseILAlgorithm class method) (GroupedPolicyBehavior static method) (PolicyBehavior static method) load_behavior() (in module navground.learning.io) load_env() (in module navground.learning.io)

load_eval_logs() (in module navground.learning.utils.sb3) load_log() (NavgroundExperiment method) load_policies() (NavgroundExperiment method) load_policy() (NavgroundExperiment method) log_directory (NavgroundExperiment property) LogField (class in navground.learning.utils.plot) logger (BaseILAlgorithm property) lowest (Indices property)

M

make_env() (in module navground.learning.utils.benchmarl) make_experiment() (in module navground.learning.evaluation) make_experiment_with_env() (in module navground.learning.evaluation) make_order_invariant_flatten_extractor() (in module navground.learning.policies.order_invariant) make_shared_parallel_env_with_env() (in module navground.learning.parallel_env) make_type() (GroupedPolicyBehavior static method) (PolicyBehavior static method) make_vec_from_env() (in module navground.learning.il) make_vec_from_penv() (in module navground.learning.il) (in module navground.learning.parallel_env) marker() (in module navground.learning.examples.pad) MaskWrapper (class in navground.learning.wrappers) max_acceleration (ControlActionConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property) max_angular_acceleration (ControlActionConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property) max_angular_speed (GroupedPolicyBehavior property) (PolicyBehavior property) max_radius (CorridorWithObstacle property) (DefaultObservationConfig attribute) (DefaultStateConfig attribute) max_speed (GroupedPolicyBehavior property) (PolicyBehavior property) max_target_distance (DefaultObservationConfig attribute) (DefaultStateConfig attribute) max_x (DefaultObservationConfig attribute) max_y (DefaultObservationConfig attribute) merge_groups_configs() (in module navground.learning.config) min_radius (CorridorWithObstacle property) min_x (DefaultObservationConfig attribute)

min_y (DefaultObservationConfig attribute) ModulationActionConfig (class in navground.learning.config) modulations (GroupedPolicyBehavior property) (PolicyBehavior property) module navground.learning navground.learning.behaviors navground.learning.behaviors.pad navground.learning.config navground.learning.env navground.learning.evaluation navground.learning.examples navground.learning.examples.corridor_with_obstacle navground.learning.examples.cross navground.learning.examples.pad navground.learning.il navground.learning.indices navground.learning.io navground.learning.onnx navground.learning.parallel_env navground.learning.policies navground.learning.probes navground.learning.register navground.learning.scenarios navground.learning.state_estimations navground.learning.types navground.learning.utils navground.learning.utils.benchmarl navground.learning.utils.plot navground.learning.utils.sb3 navground.learning.wrappers MultiAgentNavgroundEnv (class in navground.learning.parallel_env)

N

name (GroupedPolicyBehavior.Heading property) (PolicyBehavior.Heading property) NameWrapper (class in navground.learning.wrappers) navground.learning module navground.learning.behaviors module navground.learning.behaviors.pad module navground.learning.config module navground.learning.env module navground.learning.evaluation module navground.learning.examples module navground.learning.examples.corridor_with_obstacle module navground.learning.examples.cross module navground.learning.examples.pad module navground.learning.il module navground.learning.indices module navground.learning.io module navground.learning.onnx module

navground.learning.parallel_env module navground.learning.policies module navground.learning.probes module navground.learning.register module navground.learning.scenarios module navground.learning.state_estimations module navground.learning.types module navground.learning.utils module navground.learning.utils.benchmarl module navground.learning.utils.plot module navground.learning.utils.sb3 module navground.learning.wrappers module NavgroundEnv (class in navground.learning.env) NavgroundExperiment (class in navground.learning.utils.benchmarl) neighbor() (in module navground.learning.examples.pad) NetArch (in module navground.learning.policies.split_sac_policy) normalize (DefaultObservationConfig attribute) NullPolicy (class in navground.learning.policies.null_policy) NullPredictor (class in navground.learning.policies.null_predictor) NullReward (class in navground.learning.rewards)

O

observation (GroupConfig attribute) Observation (in module navground.learning.types) observation_config() (MultiAgentNavgroundEnv method) (NavgroundEnv method) observation_space (BaseILAlgorithm property) (OnnxPolicy property) observation_space() (NavgroundExperiment method) ObservationConfig (class in navground.learning.config) ObservationTransform (in module navground.learning.types)

OnnxPolicy (class in navground.learning.onnx) optimal_angular_speed (GroupedPolicyBehavior property) (PolicyBehavior property) optimal_speed (GroupedPolicyBehavior property) (PolicyBehavior property) OrderInvariantCombinedExtractor (class in navground.learning.policies.order_invariant) OrderInvariantFlattenExtractor (class in navground.learning.policies.order_invariant) orientation (GroupedPolicyBehavior property) (PolicyBehavior property)

P

pad_width (DistributedPadBehavior property) (StopAtPadBehavior property) PadReward (class in navground.learning.examples.pad) PadScenario (class in navground.learning.scenarios) parallel_env() (in module navground.learning.parallel_env) params (ModulationActionConfig attribute) path_look_ahead (GroupedPolicyBehavior property) (PolicyBehavior property) path_tau (GroupedPolicyBehavior property) (PolicyBehavior property) PathLike (in module navground.learning.types) plot_eval_logs() (in module navground.learning.utils.sb3) (NavgroundExperiment method) plot_logs() (in module navground.learning.utils.plot) plot_policy() (in module navground.learning.utils.plot) policy (BaseILAlgorithm property) (GroupConfig attribute) (NavgroundEnv property) policy_path (GroupedPolicyBehavior property) (PolicyBehavior property)

PolicyBehavior (class in navground.learning.behaviors) PolicyBehavior.Heading (class in navground.learning.behaviors) PolicyCallable (in module navground.learning.il) PolicyCallableWithInfo (in module navground.learning.il) PolicyPredictor (class in navground.learning.types) PolicyPredictorWithInfo (class in navground.learning.types) pose (GroupedPolicyBehavior property) (PolicyBehavior property) position (GroupedPolicyBehavior property) (PolicyBehavior property) predict() (OnnxPolicy method) (PolicyPredictor method) (PolicyPredictorWithInfo method) ProgressBarWithRewardCallback (class in navground.learning.utils.sb3) properties (GroupedPolicyBehavior property) (PolicyBehavior property) PyTorchObs (in module navground.learning.types) PyTorchPolicy (class in navground.learning.types)

R

radius (GroupedPolicyBehavior property) (PolicyBehavior property) RandomPolicy (class in navground.learning.policies.random_policy) RandomPredictor (class in navground.learning.policies.random_predictor) record_episode_video() (in module navground.learning.evaluation) record_run_video() (in module navground.learning.evaluation) Reduction (in module navground.learning.policies) register_schema() (GroupedPolicyBehavior static method) (PolicyBehavior static method) Registrable (class in navground.learning.register) reload_from_file() (NavgroundExperiment static method)

remove_modulation() (GroupedPolicyBehavior method) (PolicyBehavior method) render_kwargs() (in module navground.learning.scenarios.pad) reset() (MultiAgentNavgroundEnv method) (NavgroundEnv method) Reward (class in navground.learning.types) reward (GroupConfig attribute) RewardProbe (class in navground.learning.probes) rotation_tau (GroupedPolicyBehavior property) (PolicyBehavior property) run_for() (NavgroundExperiment method)

S

SACPolicyWithComm (class in navground.learning.policies.centralized_policy_with_comm) safety_margin (GroupedPolicyBehavior property) (PolicyBehavior property) save() (BaseILAlgorithm method) save_env() (in module navground.learning.io) scenario (MultiAgentNavgroundEnv property) (NavgroundEnv property) schema() (GroupedPolicyBehavior static method) (PolicyBehavior static method) SensorLike (in module navground.learning.types) sensors (GroupConfig attribute) SensorSequenceLike (in module navground.learning.types) set() (GroupedPolicyBehavior method) (PolicyBehavior method) set_env() (BaseILAlgorithm method) set_logger() (BaseILAlgorithm method) set_state_from() (GroupedPolicyBehavior method) (PolicyBehavior method) set_velocity() (GroupedPolicyBehavior method) (PolicyBehavior method) setup_tqdm() (in module navground.learning.il) shared_parallel_env() (in module navground.learning.parallel_env)

SingleAgentPolicy (class in navground.learning.utils.benchmarl) social_margin (GroupedPolicyBehavior property) (PolicyBehavior property) SocialReward (class in navground.learning.rewards) sort_keys (DefaultObservationConfig attribute) space (ActionConfig property) (BinaryControlActionConfig property) (ControlActionConfig property) (DiscreteControlActionConfig property) (DiscreteControlActionWithCommConfig property) (ModulationActionConfig property) speed (GroupedPolicyBehavior property) (PolicyBehavior property) SplitSACPolicy (class in navground.learning.policies.split_sac_policy) State (in module navground.learning.types) StateConfig (class in navground.learning.config) step() (MultiAgentNavgroundEnv method) (NavgroundEnv method) StopAtPadBehavior (class in navground.learning.behaviors.pad) sub_dict() (Indices method) sub_sequence() (Indices method) success_condition (GroupConfig attribute) SuccessProbe (class in navground.learning.probes)

T

T (in module navground.learning.indices) tag (GroupConfig attribute) target (GroupedPolicyBehavior property) (PolicyBehavior property) target_ref (GroupedPolicyBehavior property) (PolicyBehavior property) tau (StopAtPadBehavior property) terminate_on_failure (GroupConfig attribute) terminate_on_success (GroupConfig attribute) TerminationCondition (in module navground.learning.types)

to_frame() (GroupedPolicyBehavior method) (PolicyBehavior method) TrajectoryPlotConfig (class in navground.learning.evaluation) twist (GroupedPolicyBehavior property) (PolicyBehavior property) twist_from_wheel_speeds() (GroupedPolicyBehavior method) (PolicyBehavior method) twist_towards_velocity() (GroupedPolicyBehavior method) (PolicyBehavior method) type (GroupedPolicyBehavior property) (PolicyBehavior property)

U

use_absolute_frame (DefaultStateConfig attribute) use_acceleration_action (ControlActionConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property)

use_wheels (ControlActionConfig attribute) (GroupedPolicyBehavior property) (PolicyBehavior property)

V

velocity (GroupedPolicyBehavior property) (PolicyBehavior property)

VideoCallback (class in navground.learning.utils.sb3) VideoConfig (class in navground.learning.evaluation)

W

wheel_speeds (GroupedPolicyBehavior property) (PolicyBehavior property) wheel_speeds_from_twist() (GroupedPolicyBehavior method) (PolicyBehavior method)

width (CorridorWithObstacle property) with_env() (GymProbe class method) (InitPolicyBehavior class method) with_indices() (SuccessProbe class method) with_reward() (RewardProbe class method)