Reference

navground.learning

• Types
  • Array
  • Observation
  • Action
  • State
  • EpisodeStart
  • Info
  • PathLike
  • Bounds
  • SensorLike
  • SensorSequenceLike
  • ObservationTransform
  • TerminationCondition
  • IndicesLike
  • Reward
    • Reward.__call__()
  • PolicyPredictor
    • PolicyPredictor.predict()
  • PolicyPredictorWithInfo
    • PolicyPredictorWithInfo.predict()
  • AnyPolicyPredictor
  • accept_info()
  • PyTorchObs
  • PyTorchPolicy
    • PyTorchPolicy.__call__()
    • PyTorchPolicy.forward()
• Indices
  • T
  • Indices
    • Indices.all()
    • Indices.as_set()
    • Indices.from_dict()
    • Indices.intersect()
    • Indices.sub_dict()
    • Indices.sub_sequence()
    • Indices.asdict
    • Indices.lowest
  • join_indices()
• Register
  • Registrable
    • Registrable._get_dict()
    • Registrable._make_from_dict()
    • Registrable.from_dict()
    • Registrable.asdict
• Configuration
  • Actions
    • Base class
    • End-to-end
    • Communication
    • Behavior Modulation
  • Observations
    • Base class
    • Default
  • State
    • Base class
    • Default
  • Group
    • GroupConfig
    • merge_groups_configs()
• Rewards functions
  • Null
    • NullReward
  • Fixed
    • FixedReward
  • Efficacy
    • EfficacyReward
  • Social
    • SocialReward
• Single-agent Gymnasium Environment
  • BaseEnv
  • NavgroundEnv
    • NavgroundEnv.action_config()
    • NavgroundEnv.from_dict()
    • NavgroundEnv.get_cmd_from_action()
    • NavgroundEnv.observation_config()
    • NavgroundEnv.reset()
    • NavgroundEnv.step()
    • NavgroundEnv.asdict
    • NavgroundEnv.init_args
    • NavgroundEnv.policy
    • NavgroundEnv.scenario
• Multi-agent Pettingzoo Environment
  • BaseParallelEnv
  • MultiAgentNavgroundEnv
    • MultiAgentNavgroundEnv.action_config()
    • MultiAgentNavgroundEnv.from_dict()
    • MultiAgentNavgroundEnv.get_cmd_from_action()
    • MultiAgentNavgroundEnv.get_policy()
    • MultiAgentNavgroundEnv.observation_config()
    • MultiAgentNavgroundEnv.reset()
    • MultiAgentNavgroundEnv.step()
    • MultiAgentNavgroundEnv.asdict
    • MultiAgentNavgroundEnv.init_args
    • MultiAgentNavgroundEnv.scenario
  • shared_parallel_env()
  • parallel_env()
  • make_vec_from_penv()
  • make_shared_parallel_env_with_env()
  • JointEnv
• Wrappers
  • MaskWrapper
  • NameWrapper
• Policies
  • Null
    • NullPolicy
    • NullPredictor
  • Random
    • RandomPolicy
    • RandomPredictor
  • Info
    • InfoPolicy
  • Ordering-invariant extractor
    • Reduction
    • OrderInvariantCombinedExtractor
    • OrderInvariantFlattenExtractor
    • make_order_invariant_flatten_extractor()
  • Centralized training with communication (SAC)
    • SACPolicyWithComm
    • DistributedCommPolicy
  • Split MLP Policy (SAC)
    • InputSpec
    • NetArch
    • ActorSpec
    • SplitSACPolicy
    • AlternateActorCallback
• Imitation Learning
  • PolicyCallableWithInfo
  • AnyPolicy
  • PolicyCallable
  • generate_trajectories()
  • Utilities
    • make_vec_from_env()
    • make_vec_from_penv()
    • setup_tqdm()
  • Base class
    • BaseILAlgorithm
  • Behavior Cloning
    • BC
  • DAgger
    • DAgger
• Evaluation
  • Policy
    • evaluate_policy()
  • Policies
    • evaluate_policies()
  • Navground policy
    • evaluate()
    • evaluate_with_experiment()
    • evaluate_with_experiment_and_env()
  • Scenarios
    • InitPolicyBehavior
  • Experiments
    • make_experiment()
    • make_experiment_with_env()
  • Logging
    • TrajectoryPlotConfig
    • VideoConfig
    • config_eval_log()
  • Video
    • display_run_video()
    • record_run_video()
    • display_episode_video()
    • record_episode_video()
• Saving and Loading
  • save_env()
  • load_env()
  • export_behavior()
  • export_policy_as_behavior()
  • load_behavior()
• Onnx
  • Exporting
    • export()
  • Inference
    • OnnxPolicy
• Navground Components
  • Behaviors
    • PolicyBehavior
    • GroupedPolicyBehavior
    • Pad
  • Scenarios
    • CorridorWithObstacle
    • Forward
    • Pad
  • State Estimations
    • CommSensor
  • Probes
    • GymProbe
    • RewardProbe
    • SuccessProbe
    • CommProbe
• Utils
  • Plotting
    • plot_policy()
    • LogField
    • plot_logs()
  • StableBaseLine3
    • ExportOnnxCallback
    • ProgressBarWithRewardCallback
    • VideoCallback
    • load_eval_logs()
    • plot_eval_logs()
  • BenchMARL
    • NavgroundExperiment
    • SingleAgentPolicy
    • ExportPolicyCallback
    • AlternateActorCallback
    • make_env()
    • evaluate_policy()
• Examples
  • Corridor
    • get_env()
  • Crossing
    • get_env()
  • Pad
    • Environments
    • Reward
    • Sensors