{"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/application-of-self-play-reinforcement","title":"Application of Self-Play Reinforcement Learning to a Four-Player Game of Imperfect Information","arxiv_id":"1808.10442","date":"2018-08-30","proceeding":null,"authors":["Henry Charlesworth"],"abstract":"We introduce a new virtual environment for simulating a card game known as\n\"Big 2\". This is a four-player game of imperfect information with a relatively\ncomplicated action space (being allowed to play 1,2,3,4 or 5 card combinations\nfrom an initial starting hand of 13 cards). As such it poses a challenge for\nmany current reinforcement learning methods. We then use the recently proposed\n\"Proximal Policy Optimization\" algorithm to train a deep neural network to play\nthe game, purely learning via self-play, and find that it is able to reach a\nlevel which outperforms amateur human players after only a relatively short\namount of training time and without needing to search a tree of future game\nstates.","url_abs":"http://arxiv.org/abs/1808.10442v1","url_pdf":"http://arxiv.org/pdf/1808.10442v1.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":"application-of-self-play-reinforcement","repo_url":"https://github.com/henrycharlesworth/big2_PPOalgorithm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"application-of-self-play-reinforcement","repo_url":"https://github.com/jasonisgod/Big2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"card-games","task_name":"Card Games"},{"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}