Skip to yearly menu bar Skip to main content


Leveraging Procedural Generation to Benchmark Reinforcement Learning

Karl Cobbe · Chris Hesse · Jacob Hilton · John Schulman

Keywords: [ Deep Reinforcement Learning ] [ Transfer and Multitask Learning ] [ Reinforcement Learning ] [ Reinforcement Learning - Deep RL ]


We introduce Procgen Benchmark, a suite of 16 procedurally generated game-like environments designed to benchmark both sample efficiency and generalization in reinforcement learning. We believe that the community will benefit from increased access to high quality training environments, and we provide detailed experimental protocols for using this benchmark. We empirically demonstrate that diverse environment distributions are essential to adequately train and evaluate RL agents, thereby motivating the extensive use of procedural content generation. We then use this benchmark to investigate the effects of scaling model size, finding that larger models significantly improve both sample efficiency and generalization.

Chat is not available.