Skip to content

IMultiAgentImitationScholaEnvironment

Native interface for multi-agent imitation learning environments.

Provides the contract for environments that manage multiple agents, each potentially with different observation and action spaces.

Subclassed by AMultiAgentImitationPlayerController

class IMultiAgentImitationScholaEnvironment
: public IBaseImitationScholaEnvironment

Methods

InitializeEnvironment

void InitializeEnvironment(
TMap<FString, FInteractionDefinition> &OutAgentDefinitions)

Initialize the environment and define all agents and their interaction spaces.

Parameters

  • OutAgentDefinitions (TMap<FString, FInteractionDefinition>)

SeedEnvironment

void SeedEnvironment(int Seed)

Set the random seed for reproducible environment behavior.

Parameters

  • Seed (int)

SetEnvironmentOptions

void SetEnvironmentOptions(const TMap<FString, FString> &Options)

Configure environment-specific options.

Parameters

  • Options (const TMap<FString, FString>)

Reset

void Reset(TMap<FString, FInitialAgentState> &OutAgentState)

Reset the environment and return initial states for all agents.

Parameters

  • OutAgentState (TMap<FString, FInitialAgentState>)

Step

void Step(TMap<FString, FImitationAgentState> &OutAgentStates)

Execute one environment step and return imitation states for all agents.

Parameters

  • OutAgentStates (TMap<FString, FImitationAgentState>)

Source: Source/ScholaImitation/Public/Environment/MultiAgentImitationEnvironmentInterface.h