<ul><li>Imitation Learning (IL) is widely used in machine learning, but often fails to fully recover expert behavior in single-agent games.</li><li>This study investigates the impact of scaling up model and data size on IL performance.</li><li>The findings show that IL loss and mean return scale smoothly with compute budget, resulting in power laws for training compute-optimal agents.</li><li>NetHack agents trained with IL outperform previous state-of-the-art by 1.5x.</li></ul>

Scaling Laws for Imitation Learning in Single-Agent Games

Discover more