arXiv Game AI· Shinichi Arimura·· 10 d agoAI score33
Training PPO on more PCG levels and fine-tuning with DRAIL yields more human-like Super Mario Bros. play
Stack more levels: how to get general and human-like Mario playing
AI summary
The study trains PPO agents on Super Mario Bros. levels produced by PCG at increasing scale, and evaluates generalization to unseen levels on 1000 held-out test levels. Results show that increasing the number of non-repeating PCG training levels generally improves performance on unseen levels.
Source: arXiv Game AI · arxiv.org