{"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/monte-carlo-q-learning-for-general-game","title":"Monte Carlo Q-learning for General Game Playing","arxiv_id":"1802.05944","date":"2018-02-16","proceeding":null,"authors":["Hui Wang","Michael Emmerich","Aske Plaat"],"abstract":"After the recent groundbreaking results of AlphaGo, we have seen a strong\ninterest in reinforcement learning in game playing. General Game Playing (GGP)\nprovides a good testbed for reinforcement learning. In GGP, a specification of\ngames rules is given. GGP problems can be solved by reinforcement learning.\nQ-learning is one of the canonical reinforcement learning methods, and has been\nused by (Banerjee & Stone, IJCAI 2007) in GGP. In this paper we implement\nQ-learning in GGP for three small-board games (Tic-Tac-Toe, Connect Four, Hex),\nto allow comparison to Banerjee et al. As expected, Q-learning converges,\nalthough much slower than MCTS. Borrowing an idea from MCTS, we enhance\nQ-learning with Monte Carlo Search, to give QM-learning. This enhancement\nimproves the performance of pure Q-learning. We believe that QM-learning can\nalso be used to improve performance of reinforcement learning further for\nlarger games, something which we will test in future work.","url_abs":"http://arxiv.org/abs/1802.05944v2","url_pdf":"http://arxiv.org/pdf/1802.05944v2.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":"monte-carlo-q-learning-for-general-game","repo_url":"https://github.com/FrankPortman/stannis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"monte-carlo-q-learning-for-general-game","repo_url":"https://github.com/wh1992v/ggp-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"board-games","task_name":"Board Games"},{"task_slug":"q-learning","task_name":"Q-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":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.05944","atlas_url":"https://app.syntology.ai/?focus=1802.05944","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}