ABlueprintTrainer

class ABlueprintTrainer : public AAbstractTrainer

A blueprint subclass of AAbstractTrainer that implements the abstract methods.

Note: This class is designed to be subclassed in Blueprint to implement the specific training logic for an NPC.

Dependencies: AAbstractTrainer

Inherits from: public AAbstractTrainer

Public Interface

Public Functions:

virtual float ComputeReward() override

Collect a reward from the agent’s immediate environment.

Implemented by a blueprint subclass

Returns: float representing the agents reward

Returns: float

Attributes: virtual

Source: Schola/Source/Schola/Public/Training/AbstractTrainer.h (line 227, column 7)

virtual EAgentTrainingStatus ComputeStatus() override

Check if agent is in a terminal state.

Implemented by a blueprint subclass

Returns: The status of the agent which informs whether it is still running, or why it stopped.

Returns: EAgentTrainingStatus

Attributes: virtual

Source: Schola/Source/Schola/Public/Training/AbstractTrainer.h (line 234, column 22)

virtual void GetInfo(TMap<FString, FString> &Info) override

Get the Info Mapping for the Agent.

Implemented by a blueprint subclass

Parameters:

Info (TMap<FString, FString> &) – [out] A map containing additional info collected by the agent during training

Attributes: virtual

Source: Schola/Source/Schola/Public/Training/AbstractTrainer.h (line 241, column 6)

virtual void ResetTrainer() override

Reset any per Episode properties of this Trainer.

Implemented by a blueprint subclass

Attributes: virtual

Source: Schola/Source/Schola/Public/Training/AbstractTrainer.h (line 247, column 6)

virtual void OnCompletion() override

Callback function for logic when agent completes its episode.

Implemented by a blueprint subclass

Attributes: virtual

Source: Schola/Source/Schola/Public/Training/AbstractTrainer.h (line 253, column 6)

Source: Schola/Source/Schola/Public/Training/AbstractTrainer.h (line 217, column 1)