Leveraging Procedural Generation to Benchmark Reinforcement Learning
This provides a new benchmark for the RL community to evaluate sample efficiency and generalization, though it is incremental in building on existing procedural generation ideas.
The authors introduced Procgen Benchmark, a suite of 16 procedurally generated environments to benchmark reinforcement learning, and found that larger models significantly improve sample efficiency and generalization.
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.