{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:40:32Z","timestamp":1770846032678,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342540","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"4069-4075","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Multi-Layer Prioritized Fictitious Self-play in Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Chao","family":"Yue","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"}]},{"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"}]},{"given":"Lin","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"}]},{"given":"Yuan","family":"Lei","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"}]},{"given":"Shun","family":"Mao","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"}]},{"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"key":"ref3","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume":"30","author":"Lanctot","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1090\/s0002-9904-1952-09589-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/0025-5564(78)90077-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511800481.006"},{"key":"ref7","first-page":"805","article-title":"Fictitious self-play in extensive-form games","volume-title":"International conference on machine learning","author":"Heinrich"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.65109\/CHTP1993"},{"key":"ref9","article-title":"An overview of multi-agent reinforcement learning from game theoretical perspective","author":"Yang","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.65109\/DBTO3701"},{"key":"ref11","first-page":"206","article-title":"Analyzing complex strategic interactions in multiagent games","volume-title":"Proceedings of the AAAI Workshop on Game-Theoretic and Decision-Theoretic Agents (GTDT 2002)","author":"Warsh"},{"key":"ref12","first-page":"1552","article-title":"Methods for empirical game-theoretic analysis","volume":"980","author":"Wellman","year":"2006","journal-title":"AAAI"},{"key":"ref13","first-page":"536","article-title":"Planning in the presence of cost functions controlled by an adversary","volume-title":"Proceedings of the 20th International Conference on Machine Learning (ICML-03)","author":"McMahan"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/bf01386316"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3233\/faia251106"},{"key":"ref16","article-title":"Policy space diversity for non-transitive games","volume":"36","author":"Yao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"Sc-psro: A unified strategy learning method for normal-form games","author":"Hu","year":"2023"},{"key":"ref18","first-page":"45402","article-title":"Team-psro for learning approximate tmecor in large team games via cooperative reinforcement learning","volume":"36","author":"McAleer","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.65109\/DMIN4153"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1426-8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291210"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342540.pdf?arnumber=11342540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:52:24Z","timestamp":1770843144000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342540","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}