{"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/can-deep-reinforcement-learning-solve-erdos","title":"Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?","arxiv_id":"1711.02301","date":"2017-11-07","proceeding":"ICML 2018 7","authors":["Maithra Raghu","Alex Irpan","Jacob Andreas","Robert Kleinberg","Quoc V. Le","Jon Kleinberg"],"abstract":"Deep reinforcement learning has achieved many recent successes, but our\nunderstanding of its strengths and limitations is hampered by the lack of rich\nenvironments in which we can fully characterize optimal behavior, and\ncorrespondingly diagnose individual actions against such a characterization.\nHere we consider a family of combinatorial games, arising from work of Erdos,\nSelfridge, and Spencer, and we propose their use as environments for evaluating\nand comparing different approaches to reinforcement learning. These games have\na number of appealing features: they are challenging for current learning\napproaches, but they form (i) a low-dimensional, simply parametrized\nenvironment where (ii) there is a linear closed form solution for optimal\nbehavior from any state, and (iii) the difficulty of the game can be tuned by\nchanging environment parameters in an interpretable way. We use these\nErdos-Selfridge-Spencer games not only to compare different algorithms, but\ntest for generalization, make comparisons to supervised learning, analyse\nmultiagent play, and even develop a self play algorithm. Code can be found at:\nhttps://github.com/rubai5/ESS_Game","url_abs":"http://arxiv.org/abs/1711.02301v5","url_pdf":"http://arxiv.org/pdf/1711.02301v5.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":"can-deep-reinforcement-learning-solve-erdos","repo_url":"https://github.com/rubai5/ESS_Game","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"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":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}