arXiv · 2611.16175
Stack more levels: how to get general and human-like Mario playing
Abstract
Super Mario Bros. is widely used in game AI and procedural content generation (PCG), yet it remains unclear whether a model-free agent can reliably win unseen levels. To address this question, we train Proximal Policy Optimization (PPO) agents on increasingly large sets of PCG-generated Mario levels and evaluate their generalization on 1000 held-out test levels. We then shape competent PPO policies into three gameplay archetypes---runner, killer, and collector. Finally, we fine-tune these PPO policies using Diffusion-Reward Adversarial Imitation Learning (DRAIL) with human gameplay demonstrations. We find that increasing the number of distinct PCG-generated training levels generally improves unseen-level performance, and that fine-tuning PPO policies with DRAIL increases action-level human-likeness while preserving much of the persona induced by PPO pretraining.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Shinichi Arimura, Yuchen Li, Julian Togelius. 2026-11-12. Stack more levels: how to get general and human-like Mario playing. https://searcharxiv.com/abs/2611.16175
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.