{"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/deepstack-expert-level-artificial","title":"DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker","arxiv_id":"1701.01724","date":"2017-01-06","proceeding":null,"authors":["Matej Moravčík","Martin Schmid","Neil Burch","Viliam Lisý","Dustin Morrill","Nolan Bard","Trevor Davis","Kevin Waugh","Michael Johanson","Michael Bowling"],"abstract":"Artificial intelligence has seen several breakthroughs in recent years, with\ngames often serving as milestones. A common feature of these games is that\nplayers have perfect information. Poker is the quintessential game of imperfect\ninformation, and a longstanding challenge problem in artificial intelligence.\nWe introduce DeepStack, an algorithm for imperfect information settings. It\ncombines recursive reasoning to handle information asymmetry, decomposition to\nfocus computation on the relevant decision, and a form of intuition that is\nautomatically learned from self-play using deep learning. In a study involving\n44,000 hands of poker, DeepStack defeated with statistical significance\nprofessional poker players in heads-up no-limit Texas hold'em. The approach is\ntheoretically sound and is shown to produce more difficult to exploit\nstrategies than prior approaches.","url_abs":"http://arxiv.org/abs/1701.01724v3","url_pdf":"http://arxiv.org/pdf/1701.01724v3.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":"deepstack-expert-level-artificial","repo_url":"https://github.com/lifrordi/DeepStack-Leduc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"torch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"game-of-poker","task_name":"Game of Poker"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1701.01724","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}