{"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/assessing-the-potential-of-classical-q","title":"Assessing the Potential of Classical Q-learning in General Game Playing","arxiv_id":"1810.06078","date":"2018-10-14","proceeding":null,"authors":["Hui Wang","Michael Emmerich","Aske Plaat"],"abstract":"After the recent groundbreaking results of AlphaGo and AlphaZero, we have\nseen strong interests in deep reinforcement learning and artificial general\nintelligence (AGI) in game playing. However, deep learning is\nresource-intensive and the theory is not yet well developed. For small games,\nsimple classical table-based Q-learning might still be the algorithm of choice.\nGeneral Game Playing (GGP) provides a good testbed for reinforcement learning\nto research AGI. Q-learning is one of the canonical reinforcement learning\nmethods, and has been used by (Banerjee $\\&$ Stone, IJCAI 2007) in GGP. In this\npaper we implement Q-learning in GGP for three small-board games (Tic-Tac-Toe,\nConnect Four, Hex)\\footnote{source code: https://github.com/wh1992v/ggp-rl}, to\nallow comparison to Banerjee et al.. We find that Q-learning converges to a\nhigh win rate in GGP. For the $\\epsilon$-greedy strategy, we propose a first\nenhancement, the dynamic $\\epsilon$ algorithm. In addition, inspired by (Gelly\n$\\&$ Silver, ICML 2007) we combine online search (Monte Carlo Search) to\nenhance offline learning, and propose QM-learning for GGP. Both enhancements\nimprove the performance of classical Q-learning. In this work, GGP allows us to\nshow, if augmented by appropriate enhancements, that classical table-based\nQ-learning can perform well in small games.","url_abs":"http://arxiv.org/abs/1810.06078v1","url_pdf":"http://arxiv.org/pdf/1810.06078v1.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":"assessing-the-potential-of-classical-q","repo_url":"https://github.com/wh1992v/ggp-rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"board-games","task_name":"Board Games"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"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":"alphazero","method_name":"AlphaZero"},{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}