{"work":{"id":"fd9ec93d-a652-4054-ac1a-cfcada7b1dcd","openalex_id":"https://openalex.org/W2291986326","doi":"10.48550/arxiv.1603.01121","arxiv_id":"1603.01121","raw_key":null,"title":"Deep Reinforcement Learning from Self-Play in Imperfect-Information Games","authors":null,"authors_text":"Johannes Heinrich and David Silver","year":2016,"venue":"cs.LG","abstract":"Many real-world applications can be described as large-scale games of imperfect information. To deal with these challenging domains, prior work has focused on computing Nash equilibria in a handcrafted abstraction of the domain. In this paper we introduce the first scalable end-to-end approach to learning approximate Nash equilibria without prior domain knowledge. Our method combines fictitious self-play with deep reinforcement learning. When applied to Leduc poker, Neural Fictitious Self-Play (NFSP) approached a Nash equilibrium, whereas common reinforcement learning methods diverged. In Limit Texas Holdem, a poker game of real-world scale, NFSP learnt a strategy that approached the performance of state-of-the-art, superhuman algorithms based on significant domain expertise.","external_url":"https://arxiv.org/abs/1603.01121","cited_by_count":145,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"1603.01121","created_at":"2026-05-11T23:41:15.511782+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Deep Reinforcement Learning from Self-Play in Imperfect-Information Games","render_title":"Deep Reinforcement Learning from Self-Play in Imperfect-Information Games"},"hub":{"state":{"work_id":"fd9ec93d-a652-4054-ac1a-cfcada7b1dcd","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":14,"external_cited_by_count":145,"distinct_field_count":5,"first_pith_cited_at":"2019-12-13T19:56:40+00:00","last_pith_cited_at":"2026-07-07T23:11:21+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-12T17:10:10.468796+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1}],"polarity_counts":[{"context_polarity":"background","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}