Index

_

__call__() (Reward method)

A

accept_info() (in module navground.learning.types) action (GroupConfig attribute) Action (in module navground.learning.types) action_space (BaseILAlgorithm property) (OnnxPolicy property) ActionConfig (class in navground.learning.config) all() (Indices class method)

AnyPolicy (in module navground.learning.il) AnyPolicyPredictor (in module navground.learning.types) Array (in module navground.learning.types) as_set() (Indices method) asdict (GroupConfig property) (Indices property) (MultiAgentNavgroundEnv property) (NavgroundEnv 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) Bounds (in module navground.learning.types)

C

clone() (PolicyBehavior method) clone_behavior() (PolicyBehavior class method) collect_runs() (BC method) color (GroupConfig attribute)

config_eval_log() (in module navground.learning.evaluation) configure() (ActionConfig method) (ObservationConfig method) ControlActionConfig (class in navground.learning.config) CorridorWithObstacle (class in navground.learning.scenarios)

D

DAgger (class in navground.learning.il) DefaultObservationConfig (class in navground.learning.config)

deterministic (GroupConfig attribute) (PolicyBehavior property) dtype (RewardProbe attribute)

E

EfficacyReward (class in navground.learning.rewards) env (BaseILAlgorithm property) EpisodeStart (in module navground.learning.types) evaluate() (in module navground.learning.evaluation) evaluate_policies() (in module navground.learning.evaluation)

evaluate_policy() (in module navground.learning.evaluation) 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_policy_as_behavior() (in module navground.learning.io)

F

fix_orientation (ControlActionConfig attribute) (PolicyBehavior property) flat (DefaultObservationConfig attribute) (PolicyBehavior property)

ForwardScenario (class in navground.learning.scenarios) from_dict() (Indices class method) (MultiAgentNavgroundEnv class method) (NavgroundEnv class method)

G

generate_trajectories() (in module navground.learning.il.rollout) get_action() (ActionConfig method) get_cmd_from_action() (ActionConfig method) get_env() (BaseILAlgorithm method) (in module navground.learning.examples.corridor_with_obstacle) (in module navground.learning.examples.cross)

get_policy() (MultiAgentNavgroundEnv method) GroupConfig (class in navground.learning.config) GymProbe (class in navground.learning.probes)

H

has_wheels (ControlActionConfig attribute) history (DefaultObservationConfig attribute) (ObservationConfig property) (PolicyBehavior property)

I

include_angular_speed (DefaultObservationConfig attribute) include_radius (DefaultObservationConfig attribute) (PolicyBehavior property) include_target_angular_speed (DefaultObservationConfig attribute) (PolicyBehavior property) include_target_direction (DefaultObservationConfig attribute) (PolicyBehavior property) include_target_direction_validity (DefaultObservationConfig attribute) (PolicyBehavior property) include_target_distance (DefaultObservationConfig attribute) (PolicyBehavior property) include_target_distance_validity (DefaultObservationConfig attribute) (PolicyBehavior property) include_target_speed (DefaultObservationConfig attribute) (PolicyBehavior property)

include_velocity (DefaultObservationConfig attribute) (PolicyBehavior property) 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_world() (CorridorWithObstacle method) (ForwardScenario method) InitPolicyBehavior (class in navground.learning.evaluation) intersect() (Indices method) is_configured() (ActionConfig method) (ObservationConfig method)

L

learn() (BaseILAlgorithm method) length (CorridorWithObstacle property) load() (BaseILAlgorithm class method)

load_behavior() (in module navground.learning.io) load_env() (in module navground.learning.io) logger (BaseILAlgorithm property) lowest (Indices property)

M

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_vec_from_env() (in module navground.learning.il) make_vec_from_penv() (in module navground.learning.il) (in module navground.learning.parallel_env) max_acceleration (ControlActionConfig attribute) (PolicyBehavior property) max_angular_acceleration (ControlActionConfig attribute) (PolicyBehavior property) max_radius (CorridorWithObstacle property) (DefaultObservationConfig attribute) max_target_distance (DefaultObservationConfig attribute) merge_groups_configs() (in module navground.learning.config) min_radius (CorridorWithObstacle property) ModulationActionConfig (class in navground.learning.config) module navground.learning navground.learning.behaviors navground.learning.config navground.learning.env navground.learning.evaluation navground.learning.examples navground.learning.examples.corridor_with_obstacle navground.learning.examples.cross navground.learning.il navground.learning.indices navground.learning.io navground.learning.onnx navground.learning.parallel_env navground.learning.policies navground.learning.probes navground.learning.scenarios navground.learning.types

MultiAgentNavgroundEnv (class in navground.learning.parallel_env)

N

navground.learning module navground.learning.behaviors 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.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.scenarios module navground.learning.types module NavgroundEnv (class in navground.learning.env) 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_space (BaseILAlgorithm property) (OnnxPolicy property)

ObservationConfig (class in navground.learning.config) OnnxPolicy (class in navground.learning.onnx) OrderInvariantCombinedExtractor (class in navground.learning.policies.order_invariant) OrderInvariantFlattenExtractor (class in navground.learning.policies.order_invariant)

P

parallel_env() (in module navground.learning.parallel_env) params (ModulationActionConfig attribute) PathLike (in module navground.learning.types) policy (BaseILAlgorithm property) (GroupConfig attribute) (NavgroundEnv property) policy_path (PolicyBehavior property)

PolicyBehavior (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) predict() (OnnxPolicy method) (PolicyPredictor method) (PolicyPredictorWithInfo method)

R

RandomPolicy (class in navground.learning.policies.random_policy) RandomPredictor (class in navground.learning.policies.random_predictor) Reduction (in module navground.learning.policies) reset() (MultiAgentNavgroundEnv method) (NavgroundEnv method)

Reward (class in navground.learning.types) reward (GroupConfig attribute) RewardProbe (class in navground.learning.probes)

S

save() (BaseILAlgorithm method) save_env() (in module navground.learning.io) scenario (MultiAgentNavgroundEnv property) (NavgroundEnv property) sensor (GroupConfig attribute) set_env() (BaseILAlgorithm method) set_logger() (BaseILAlgorithm method) setup_tqdm() (in module navground.learning.il) shared_parallel_env() (in module navground.learning.parallel_env)

SocialReward (class in navground.learning.rewards) space (ActionConfig property) (ControlActionConfig property) (ModulationActionConfig property) State (in module navground.learning.types) step() (MultiAgentNavgroundEnv method) (NavgroundEnv method) sub_dict() (Indices method) sub_sequence() (Indices method)

T

T (in module navground.learning.indices)

tag (GroupConfig attribute) TrajectoryPlotConfig (class in navground.learning.evaluation)

U

use_acceleration_action (ControlActionConfig attribute) (PolicyBehavior property)

use_wheels (ControlActionConfig attribute) (PolicyBehavior property)

V

VideoConfig (class in navground.learning.evaluation)

W

width (CorridorWithObstacle property) with_env() (GymProbe class method) (InitPolicyBehavior class method)

with_reward() (RewardProbe class method)