Combining Evolutionary Search with Behaviour Cloning for Procedurally Generated Content

TL;DR

This paper introduces a hybrid method combining evolutionary search and behaviour cloning to efficiently generate diverse video game levels, reducing generation time while maintaining quality.

Contribution

It presents a novel framework that leverages evolutionary search to produce training data for behaviour cloning, enabling faster level generation in procedural content creation.

Findings

Reduces level generation time significantly.

Maintains diversity and quality of generated levels.

Effective in maze and Super Mario Bros levels.

Abstract

In this work, we consider the problem of procedural content generation for video game levels. Prior approaches have relied on evolutionary search (ES) methods capable of generating diverse levels, but this generation procedure is slow, which is problematic in real-time settings. Reinforcement learning (RL) has also been proposed to tackle the same problem, and while level generation is fast, training time can be prohibitively expensive. We propose a framework to tackle the procedural content generation problem that combines the best of ES and RL. In particular, our approach first uses ES to generate a sequence of levels evolved over time, and then uses behaviour cloning to distil these levels into a policy, which can then be queried to produce new levels quickly. We apply our approach to a maze game and Super Mario Bros, with our results indicating that our approach does in fact decrease the time required for level generation, especially when an increasing number of valid levels are required.