Automated Game Design via Conceptual Expansion

TL;DR

This paper presents a novel machine learning-based method for automated game design that recombines learned representations of existing games through conceptual expansion, enabling the creation of new games without relying on hand-authored knowledge.

Contribution

It introduces the first machine learning-based system for automated game design using conceptual expansion to recombine learned game representations.

Findings

Successfully recreates existing games

Demonstrates potential for generating new games

First approach of its kind using machine learning

Abstract

Automated game design has remained a key challenge within the field of Game AI. In this paper, we introduce a method for recombining existing games to create new games through a process called conceptual expansion. Prior automated game design approaches have relied on hand-authored or crowd-sourced knowledge, which limits the scope and applications of such systems. Our approach instead relies on machine learning to learn approximate representations of games. Our approach recombines knowledge from these learned representations to create new games via conceptual expansion. We evaluate this approach by demonstrating the ability for the system to recreate existing games. To the best of our knowledge, this represents the first machine learning-based automated game design system.