1. Epic GamesDeveloper
  3. ULearningAgentsImitationTrainer

ULearningAgentsImitationTrainer

The [ULearningAgentsImitationTrainer](API\Plugins\LearningAgentsTraining\ULearningAgentsImitationTrainer) enable imitation learning, i.e. learning from human/AI demonstrations.

API > API/Plugins > API/Plugins/LearningAgentsTraining

Inheritance Hierarchy

References

   
Module LearningAgentsTraining
Header /Engine/Plugins/Experimental/LearningAgents/Source/LearningAgentsTraining/Public/LearningAgentsImitationTrainer.h
Include #include "LearningAgentsImitationTrainer.h"

Syntax

UCLASS&40;BlueprintType, Blueprintable&41;  
class ULearningAgentsImitationTrainer : public UActorComponent

Remarks

The ULearningAgentsImitationTrainer enable imitation learning, i.e. learning from human/AI demonstrations. Imitation training is typically much faster than reinforcement learning, but requires gathering large amounts of data in order to generalize. This can be used to initialize a reinforcement learning policy to speed up initial exploration.

Constructors

  Type Name Description
Public function   Setup
Public function    

Destructors

  Type Name Description
Public function Virtual    

Functions

  Type Name Description
Public function UFunction BlueprintCallable, Category void

BeginTraining ( ULearningAgentsPolicy* InPolicy,
const ULearningAgentsRecording* Recording,
const FLearningAgentsImitationTrainerSettings& ImitationTrainerSettings,
const FLearningAgentsImitationTrainerTrainingSettings& ImitationTrainerTrainingSettings,
const FLearningAgentsTrainerPathSettings& ImitationTrainerPathSettings,
const bool bReinitializePolicyNetwork
)

 Begins the training process with the provided settings.
Public function UFunction BlueprintCallable, Category void Stops the training process.
Public function Const UFunction BlueprintPure, Category bool Returns true if the trainer has failed to communicate with the external training process.
Public function Const UFunction BlueprintPure, Category bool Returns true if the trainer is currently training; Otherwise, false.
Public function UFunction BlueprintCallable, Category void Iterates the training process and gets the updated policy network.
Public function UFunction BlueprintCallable, Category void

RunTraining ( ULearningAgentsPolicy* InPolicy,
const ULearningAgentsRecording* Recording,
const FLearningAgentsImitationTrainerSettings& ImitationTrainerSettings,
const FLearningAgentsImitationTrainerTrainingSettings& ImitationTrainerTrainingSettings,
const FLearningAgentsTrainerPathSettings& ImitationTrainerPathSettings,
const bool bReinitializePolicyNetwork
)

 Convenience function that runs a basic training loop.

Overridden from UActorComponent

  Type Name Description
Public function Virtual void

EndPlay ( const EEndPlayReason::Type EndPlayReason
)

 Will automatically call EndTraining if training is still in-progress when play is ending.

See Also

ULearningAgentsInteractor to understand how observations and actions work.

ULearningAgentsController to understand how we can manually perform actions via a human or AI.

ULearningAgentsRecorder to understand how to make new recordings.

Ask questions and help your peers Developer Forums

Write your own tutorials or read those from others Learning Library

On this page