Skip to content

USimpleStepper

Simple synchronous stepper implementation.

A straightforward stepper that performs the full observation-inference-action loop synchronously on the calling thread. On each Step() call:Collects observations from all agents Performs batched inference using the policy Applies the resulting actions to the agents

This stepper blocks during policy inference and is suitable for simple scenarios or policies with fast inference times.

class USimpleStepper : public UObject, public IStepper

Methods

Init

inline virtual bool Init(const TArray<TScriptInterface<IAgent>> &InAgents,
                         const TScriptInterface<IPolicy> &InPolicy) override

Initialize the stepper with the given agents and policy.

Parameters

  • InAgents (const TArray<TScriptInterface<IAgent>>)

  • InPolicy (const TScriptInterface<IPolicy>)

Step

inline void Step()

Execute one step of the agent-policy loop.

Attributes

Agents

TArray<TScriptInterface<IAgent>> Agents

Agents stepped each tick in array order.

Policy

TScriptInterface<IPolicy> Policy

Policy used for inference in Step().

Source: Source/ScholaInferenceUtils/Public/Steppers/SimpleStepper.h