{"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/revisiting-the-arcade-learning-environment","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","arxiv_id":"1709.06009","date":"2017-09-18","proceeding":null,"authors":["Marlos C. Machado","Marc G. Bellemare","Erik Talvitie","Joel Veness","Matthew Hausknecht","Michael Bowling"],"abstract":"The Arcade Learning Environment (ALE) is an evaluation platform that poses\nthe challenge of building AI agents with general competency across dozens of\nAtari 2600 games. It supports a variety of different problem settings and it\nhas been receiving increasing attention from the scientific community, leading\nto some high-profile success stories such as the much publicized Deep\nQ-Networks (DQN). In this article we take a big picture look at how the ALE is\nbeing used by the research community. We show how diverse the evaluation\nmethodologies in the ALE have become with time, and highlight some key concerns\nwhen evaluating agents in the ALE. We use this discussion to present some\nmethodological best practices and provide new benchmark results using these\nbest practices. To further the progress in the field, we introduce a new\nversion of the ALE that supports multiple game modes and provides a form of\nstochasticity we call sticky actions. We conclude this big picture look by\nrevisiting challenges posed when the ALE was introduced, summarizing the\nstate-of-the-art in various problems and highlighting problems that remain\nopen.","url_abs":"http://arxiv.org/abs/1709.06009v2","url_pdf":"http://arxiv.org/pdf/1709.06009v2.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":"revisiting-the-arcade-learning-environment","repo_url":"https://github.com/bclyang/updated-atari-env","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"revisiting-the-arcade-learning-environment","repo_url":"https://github.com/floringogianu/atari-agents","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"revisiting-the-arcade-learning-environment","repo_url":"https://github.com/glenn89/FederatedRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"revisiting-the-arcade-learning-environment","repo_url":"https://github.com/jessefarebro/dqn-ale","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"revisiting-the-arcade-learning-environment","repo_url":"https://github.com/link-kut/rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"revisiting-the-arcade-learning-environment","repo_url":"https://github.com/openrlbenchmark/openrlbenchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"revisiting-the-arcade-learning-environment","repo_url":"https://github.com/mgbellemare/Arcade-Learning-Environment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.06009","atlas_url":"https://app.syntology.ai/?focus=1709.06009","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}