Procedural Content Generation using Neuroevolution and Novelty Search for Diverse Video Game Levels

Abstract

Procedurally generated video game content has the potential to drastically reduce the content creation budget of game developers and large studios. However, adoption is hindered by limitations such as slow generation, as well as low quality and diversity of content. We introduce an evolutionary search-based approach for evolving level generators using novelty search to procedurally generate diverse levels in real time, without requiring training data or detailed domain-specific knowledge. We test our method on two domains, and our results show an order of magnitude speedup in generation time compared to existing methods while obtaining comparable metric scores. We further demonstrate the ability to generalise to arbitrary-sized levels without retraining.

arXiv commentAccepted to the Genetic and Evolutionary Computation Conference (GECCO '22), July 9--13, 2022, Boston, MA, USA. Code is located at https://github.com/Michael-Beukman/PCGNN

References in corpus (8)

• Generative Adversarial Networks: An Overview
• Illuminating search spaces by mapping elites
• Procedural Content Generation through Quality Diversity
• Evolution of Swarm Robotics Systems with Novelty Search
• Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation
• CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation
• Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros Study
• Towards Objective Metrics for Procedurally Generated Video Game Levels

Cited by in corpus (2)

• Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizes
• Quantum Wave Function Collapse for Procedural Content Generation