_version_ 1866916115565772800
author Huang, Shengyi
Gallouédec, Quentin
Felten, Florian
Raffin, Antonin
Dossa, Rousslan Fernand Julien
Zhao, Yanxiao
Sullivan, Ryan
Makoviychuk, Viktor
Makoviichuk, Denys
Danesh, Mohamad H.
Roumégous, Cyril
Weng, Jiayi
Chen, Chufan
Rahman, Md Masudur
Araújo, João G. M.
Quan, Guorui
Tan, Daniel
Klein, Timo
Charakorn, Rujikorn
Towers, Mark
Berthelot, Yann
Mehta, Kinal
Chakraborty, Dipam
KG, Arjun
Charraut, Valentin
Ye, Chang
Liu, Zichen
Alegre, Lucas N.
Nikulin, Alexander
Hu, Xiao
Liu, Tianlin
Choi, Jongwook
Yi, Brent
author_facet Huang, Shengyi
Gallouédec, Quentin
Felten, Florian
Raffin, Antonin
Dossa, Rousslan Fernand Julien
Zhao, Yanxiao
Sullivan, Ryan
Makoviychuk, Viktor
Makoviichuk, Denys
Danesh, Mohamad H.
Roumégous, Cyril
Weng, Jiayi
Chen, Chufan
Rahman, Md Masudur
Araújo, João G. M.
Quan, Guorui
Tan, Daniel
Klein, Timo
Charakorn, Rujikorn
Towers, Mark
Berthelot, Yann
Mehta, Kinal
Chakraborty, Dipam
KG, Arjun
Charraut, Valentin
Ye, Chang
Liu, Zichen
Alegre, Lucas N.
Nikulin, Alexander
Hu, Xiao
Liu, Tianlin
Choi, Jongwook
Yi, Brent
contents 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, 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. Open RL Benchmark 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. Open RL Benchmark 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, Open RL Benchmark 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 Open RL Benchmark in practice. To the best of our knowledge, Open RL Benchmark 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03046
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning
Huang, Shengyi
Gallouédec, Quentin
Felten, Florian
Raffin, Antonin
Dossa, Rousslan Fernand Julien
Zhao, Yanxiao
Sullivan, Ryan
Makoviychuk, Viktor
Makoviichuk, Denys
Danesh, Mohamad H.
Roumégous, Cyril
Weng, Jiayi
Chen, Chufan
Rahman, Md Masudur
Araújo, João G. M.
Quan, Guorui
Tan, Daniel
Klein, Timo
Charakorn, Rujikorn
Towers, Mark
Berthelot, Yann
Mehta, Kinal
Chakraborty, Dipam
KG, Arjun
Charraut, Valentin
Ye, Chang
Liu, Zichen
Alegre, Lucas N.
Nikulin, Alexander
Hu, Xiao
Liu, Tianlin
Choi, Jongwook
Yi, Brent
Machine Learning
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, 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. Open RL Benchmark 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. Open RL Benchmark 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, Open RL Benchmark 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 Open RL Benchmark in practice. To the best of our knowledge, Open RL Benchmark 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.
title Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2402.03046