Skip to content

NevarokML: Discrete Space

The NevarokML plugin provides a Discrete space implementation, representing a discrete space with values in the set {0, 1, ..., n-1}. It is commonly used to define the action space in reinforcement learning environments where the agent can choose from a finite number of actions.

Discrete Space Overview

The Discrete space in NevarokML corresponds to a discrete set of values ranging from 0 to n-1. It is used to represent the action space in reinforcement learning environments. Here's the key feature and parameter of the Discrete space:

  • owner: Parameter represents the owner of the space object, usually the object creating the space.
  • size (N): The size of the discrete space, indicating the number of possible values the space can take.


Here is the API for the Discrete space in NevarokML, along with the corresponding default parameter settings:

#include "Spaces/NevarokMLSpace.h"

UFUNCTION(BlueprintPure, Category = "NevarokML|Space")
static UNevarokMLSpace* Discrete(UObject* owner, int64 size = 1)

To create a Discrete space, call the Discrete factory function and provide the required parameters. The function will return an instance of the UNevarokMLSpace class, representing the Discrete space.