Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning

Shengyi Huang, Quentin Gallouédec, Florian Felten, Antonin Raffin, Rousslan Fernand Julien Dossa, Yanxiao Zhao, Ryan Sullivan, Viktor Makoviychuk, Denys Makoviichuk, Mohamad Hosein Danesh, Cyril Roumegous, Jiayi Weng, Chufan Chen, Md Masudur Rahman, João Guilherme Madeira Araújo, Guorui Quan, Daniel Chee Hian Tan, Timo Klein, Rujikorn Charakorn, Mark Towers et al. (13 additional authors not shown)

Keywords: reinforcement learning, benchmark, reproductibility

Abstract: In many Reinforcement Learning (RL) papers, learning curves are useful indicators to measure the effectiveness of RL algorithms. However, the complete raw data of the learning curves are rarely available. As a result, it is usually necessary to reproduce the experiments from scratch, which can be time-consuming and error-prone. We present Open RL Benchmark (ORLB), a set of fully tracked RL experiments, including not only the usual data such as episodic return, but also all algorithm-specific and system metrics. ORLB is community-driven: anyone can download, use, and contribute to the data. At the time of writing, more than 25,000 runs have been tracked, for a cumulative duration of more than 8 years. It covers a wide range of RL libraries and reference implementations. Special care is taken to ensure that each experiment is precisely reproducible by providing not only the full parameters, but also the versions of the dependencies used to generate it. In addition, ORLB comes with a command-line interface (CLI) for easy fetching and generating figures to present the results. In this document, we include two case studies to demonstrate the usefulness of ORLB in practice. To the best of our knowledge, ORLB is the first RL benchmark of its kind, and the authors hope that it will improve and facilitate the work of researchers in the field.

Submission Number: 402