“Procgen Benchmark: We’re Releasing Procgen Benchmark, 16 Simple-To-Use Procedurally-Generated Environments Which Provide a Direct Measure of How Quickly a Reinforcement Learning Agent Learns Generalizable Skills”, 2019-12-03 (; backlinks; similar):
Announcement of Procgen: “Leveraging Procedural Generation to Benchmark Reinforcement Learning”, et al 2019:
In this report, 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 substantially improve both sample efficiency and generalization.
…We want the best of both worlds: a benchmark comprised of many diverse environments, each of which fundamentally requires generalization. To fulfill this need, we have created Procgen Benchmark. CoinRun [ et al 2018] now serves as the inaugural environment in Procgen Benchmark, contributing its diversity to a greater whole.
…We’ve found that all of the Procgen environments require training on 500–1000 different levels before they can generalize to new levels, which suggests that standard RL benchmarks need much more diversity within each environment. Procgen Benchmark has become the standard research platform used by the OpenAI RL team, and we hope that it accelerates the community in creating better RL algorithms. [cf. Neural MMO]