Class IMultiAgentImitationScholaEnvironment
Class IMultiAgentImitationScholaEnvironment
- Defined in File MultiAgentImitationEnvironmentInterface.h
Inheritance Relationships
Base Type
public IBaseImitationScholaEnvironment(Class IBaseImitationScholaEnvironment)
class IMultiAgentImitationScholaEnvironment : public IBaseImitationScholaEnvironmentSource: Source/Schola/Imitation/Public/Environment/MultiAgentImitationEnvironmentInterface.h
Dependencies: FImitationAgentState, FInitialAgentState, FInteractionDefinition
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.
Public Functions
| Symbol | Details |
|---|---|
InitializeEnvironment | Initialize the environment and define all agents and their interaction spaces. |
SeedEnvironment | Set the random seed for reproducible environment behavior. |
SetEnvironmentOptions | Configure environment-specific options. |
Reset | Reset the environment and return initial states for all agents. |
Step | Execute one environment step and return imitation states for all agents. |
InitializeEnvironment
void InitializeEnvironment( TMap<FString, FInteractionDefinition> &OutAgentDefinitions)Initialize the environment and define all agents and their interaction spaces.
Parameters
OutAgentDefinitions – [out] Map from agent names to their interaction definitions (observation/action spaces)
| # | Direction | Name | Type | Description |
|---|---|---|---|---|
| 1 | — | OutAgentDefinitions | TMap< FString, FInteractionDefinition > & | Map from agent names to their interaction definitions (observation/action spaces) |
Source: Source/Schola/Imitation/Public/Environment/MultiAgentImitationEnvironmentInterface.h
SeedEnvironment
void SeedEnvironment(int Seed)Set the random seed for reproducible environment behavior.
Parameters
Seed – [in] The random seed value
| # | Direction | Name | Type | Description |
|---|---|---|---|---|
| 1 | — | Seed | int | The random seed value |
Source: Source/Schola/Imitation/Public/Environment/MultiAgentImitationEnvironmentInterface.h
SetEnvironmentOptions
void SetEnvironmentOptions(const TMap<FString, FString> &Options)Configure environment-specific options.
Parameters
Options – [in] Map of option names to their string values
| # | Direction | Name | Type | Description |
|---|---|---|---|---|
| 1 | — | Options | const TMap< FString, FString > & | Map of option names to their string values |
Source: Source/Schola/Imitation/Public/Environment/MultiAgentImitationEnvironmentInterface.h
Reset
void Reset(TMap<FString, FInitialAgentState> &OutAgentState)Reset the environment and return initial states for all agents.
Parameters
OutAgentState – [out] Map from agent names to their initial states
| # | Direction | Name | Type | Description |
|---|---|---|---|---|
| 1 | — | OutAgentState | TMap< FString, FInitialAgentState > & | Map from agent names to their initial states |
Source: Source/Schola/Imitation/Public/Environment/MultiAgentImitationEnvironmentInterface.h
Step
void Step(TMap<FString, FImitationAgentState> &OutAgentStates)Execute one environment step and return imitation states for all agents.
Parameters
OutAgentStates – [out] Map from agent names to their imitation states (observations, expert actions, rewards)
| # | Direction | Name | Type | Description |
|---|---|---|---|---|
| 1 | — | OutAgentStates | TMap< FString, FImitationAgentState > & | Map from agent names to their imitation states (observations, expert actions, rewards) |
Source: Source/Schola/Imitation/Public/Environment/MultiAgentImitationEnvironmentInterface.h