{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T04:15:31Z","timestamp":1749096931851,"version":"3.41.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U20B2070","61976199"],"award-info":[{"award-number":["U20B2070","61976199"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tnnls.2024.3457509","type":"journal-article","created":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T19:17:30Z","timestamp":1734031050000},"page":"11258-11270","source":"Crossref","is-referenced-by-count":1,"title":["Purified Policy Space Response Oracles for Symmetric Zero-Sum Games"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0025-8306","authenticated-orcid":false,"given":"Zhengdao","family":"Shao","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4345-856X","authenticated-orcid":false,"given":"Liansheng","family":"Zhuang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihong","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shafei","family":"Wang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/080720826"},{"key":"ref2","article-title":"Real world games look like spinning Tops","author":"Marian Czarnecki","year":"2020","journal-title":"arXiv:2004.09468"},{"key":"ref3","article-title":"Open-ended learning in symmetric zero-sum games","author":"Balduzzi","year":"2019","journal-title":"arXiv:1901.08106"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/880"},{"key":"ref5","first-page":"17443","article-title":"Real world games look like spinning Tops","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Czarnecki"},{"key":"ref6","first-page":"20238","article-title":"Pipeline PSRO: A scalable approach for finding approximate nash equilibria in large games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"McAleer"},{"key":"ref7","first-page":"536","article-title":"Planning in the presence of cost functions controlled by an adversary","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"McMahan"},{"key":"ref8","first-page":"1","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lanctot"},{"key":"ref9","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"issue":"1","key":"ref10","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1016\/j.jet.2005.12.010","article-title":"Brown\u2019s original fictitious play","volume":"135","author":"Berger","year":"2007","journal-title":"J. Econ. Theory"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref12","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"key":"ref14","first-page":"8514","article-title":"Modelling behavioural diversity for learning in open-ended games","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Perez-Nieves"},{"key":"ref15","article-title":"Unifying behavioral and response diversity for open-ended learning in zero-sum games","author":"Liu","year":"2021","journal-title":"arXiv:2106.04958"},{"key":"ref16","first-page":"1","article-title":"Policy space diversity for non-transitive games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yao"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0419-x"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1110.0500"},{"key":"ref19","first-page":"793","article-title":"Deep counterfactual regret minimization","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Brown"},{"key":"ref20","article-title":"Deep reinforcement learning from self-play in imperfect-information games","author":"Heinrich","year":"2016","journal-title":"arXiv:1603.01121"},{"key":"ref21","article-title":"DREAM: Deep regret minimization with advantage baselines and model-free learning","author":"Steinberger","year":"2020","journal-title":"arXiv:2006.10410"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref23","article-title":"Evolutionary population curriculum for scaling multi-agent reinforcement learning","author":"Long","year":"2020","journal-title":"arXiv:2003.10423"},{"key":"ref24","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017","journal-title":"arXiv:1703.03864"},{"key":"ref25","article-title":"Evolving reinforcement learning algorithms","author":"Co-Reyes","year":"2021","journal-title":"arXiv:2101.03958"},{"issue":"5","key":"ref26","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1016\/0165-1889(94)00819-4","article-title":"Consistency and cautious fictitious play","volume":"19","author":"Fudenberg","year":"1995","journal-title":"J. Econ. Dyn. Control"},{"issue":"2","key":"ref27","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.geb.2005.08.005","article-title":"Generalised weakened fictitious play","volume":"56","author":"Leslie","year":"2006","journal-title":"Games Econ. Behav."},{"key":"ref28","article-title":"Suphx: Mastering mahjong with deep reinforcement learning","author":"Li","year":"2020","journal-title":"arXiv:2003.13590"},{"key":"ref29","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"Silver","year":"2017","journal-title":"arXiv:1712.01815"},{"key":"ref30","first-page":"805","article-title":"Fictitious self-play in extensiveform games","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Heinrich"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3250523"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"key":"ref34","article-title":"A generalized training approach for multiagent learning","author":"M\u00fcller","year":"2019","journal-title":"arXiv:1909.12823"},{"key":"ref35","article-title":"Neural auto-curricula","author":"Feng","year":"2021","journal-title":"arXiv:2106.02745"},{"key":"ref36","article-title":"Anytime PSRO for two-player zero-sum games","author":"McAleer","year":"2022","journal-title":"arXiv:2201.07700"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447319"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2024.3361178"},{"issue":"1","key":"ref40","first-page":"1","article-title":"Overlapping graph clustering in attributed networks via generalized cluster potential game","volume":"18","author":"Li","year":"2023","journal-title":"ACM Trans. Knowl. Discovery Data"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2023.3297331"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599359"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref44","article-title":"Approximate exploitability: Learning a best response in large games","author":"Timbers","year":"2020","journal-title":"arXiv:2004.09677"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/66"},{"key":"ref46","first-page":"9","article-title":"AlphaHoldem: Highperformance artificial intelligence for heads-up no-limit Texas hold\u2019em from end-to-end reinforcement learning","volume-title":"Proc. AAAI","author":"Zhao"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3274547"},{"key":"ref49","first-page":"17","article-title":"Decisiontheoretic clustering of strategies","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Bard"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11022714\/10795441.pdf?arnumber=10795441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T17:57:42Z","timestamp":1749059862000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10795441\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":49,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3457509","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}