{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-reinforcement-learning-that-matters","title":"Deep Reinforcement Learning that Matters","arxiv_id":"1709.06560","date":"2017-09-19","proceeding":null,"authors":["Peter Henderson","Riashat Islam","Philip Bachman","Joelle Pineau","Doina Precup","David Meger"],"abstract":"In recent years, significant progress has been made in solving challenging\nproblems across various domains using deep reinforcement learning (RL).\nReproducing existing work and accurately judging the improvements offered by\nnovel methods is vital to sustaining this progress. Unfortunately, reproducing\nresults for state-of-the-art deep RL methods is seldom straightforward. In\nparticular, non-determinism in standard benchmark environments, combined with\nvariance intrinsic to the methods, can make reported results tough to\ninterpret. Without significance metrics and tighter standardization of\nexperimental reporting, it is difficult to determine whether improvements over\nthe prior state-of-the-art are meaningful. In this paper, we investigate\nchallenges posed by reproducibility, proper experimental techniques, and\nreporting procedures. We illustrate the variability in reported metrics and\nresults when comparing against common baselines and suggest guidelines to make\nfuture results in deep RL more reproducible. We aim to spur discussion about\nhow to ensure continued progress in the field by minimizing wasted effort\nstemming from results that are non-reproducible and easily misinterpreted.","url_abs":"http://arxiv.org/abs/1709.06560v3","url_pdf":"http://arxiv.org/pdf/1709.06560v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-reinforcement-learning-that-matters","repo_url":"https://github.com/Dascka/dl_q-learning_comparator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-reinforcement-learning-that-matters","repo_url":"https://github.com/YuhangSong/Mega-Reward","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-reinforcement-learning-that-matters","repo_url":"https://github.com/inoryy/reaver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-reinforcement-learning-that-matters","repo_url":"https://github.com/chainer/chainerrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.06560","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}