{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T18:10:02Z","timestamp":1749060602560,"version":"3.41.0"},"reference-count":43,"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\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["JQ22010"],"award-info":[{"award-number":["JQ22010"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2241243"],"award-info":[{"award-number":["U2241243"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["JQ22010"],"award-info":[{"award-number":["JQ22010"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176025","62301066","U21B2045","62206012"],"award-info":[{"award-number":["62176025","62301066","U21B2045","62206012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2023RC72"],"award-info":[{"award-number":["2023RC72"]}],"id":[{"id":"10.13039\/501100012226","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.2025.3550827","type":"journal-article","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T21:55:58Z","timestamp":1744062958000},"page":"9893-9904","source":"Crossref","is-referenced-by-count":0,"title":["Distributed Policy Space Response Oracles in Two-Player Zero-Sum Games"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1366-3749","authenticated-orcid":false,"given":"Hongsong","family":"Tang","sequence":"first","affiliation":[{"name":"School of Science, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Yingzhuo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Letian","family":"Ni","sequence":"additional","affiliation":[{"name":"School of Science, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8486-6255","authenticated-orcid":false,"given":"Liuyu","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8132-5613","authenticated-orcid":false,"given":"Yaodong","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3357-5754","authenticated-orcid":false,"given":"Ke","family":"Bi","sequence":"additional","affiliation":[{"name":"School of Science, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3433-8435","authenticated-orcid":false,"given":"Zhaofeng","family":"He","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"621","article-title":"Towards playing full MOBA games with deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ye"},{"key":"ref2","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref4","article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play StarCraft combat games","author":"Peng","year":"2017","journal-title":"arXiv:1703.10069"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029475"},{"key":"ref6","first-page":"11881","article-title":"Honor of kings arena: An environment for generalization in competitive reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hua"},{"key":"ref7","first-page":"47554","article-title":"A robust and opponent-aware league training method for starcraft II","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Huang"},{"key":"ref8","first-page":"17443","article-title":"Real world games look like spinning Tops","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Czarnecki"},{"key":"ref9","article-title":"Diverse auto-curriculum is critical for successful real-world multiagent learning systems","author":"Yang","year":"2021","journal-title":"arXiv:2102.07659"},{"key":"ref10","first-page":"4190","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lanctot"},{"key":"ref11","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":"ref12","article-title":"Online double Oracle","volume-title":"arXiv:2103.07780","author":"Dinh","year":"2021"},{"key":"ref13","first-page":"23128","article-title":"XDO: A double Oracle algorithm for extensive-form games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"McAleer"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref15","article-title":"A generalised method for empirical game theoretic analysis","author":"Tuyls","year":"2018","journal-title":"arXiv:1803.06376"},{"key":"ref16","first-page":"1552","article-title":"Methods for empirical game-theoretic analysis","volume-title":"Proc. AAAI","author":"Wellman"},{"key":"ref17","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":"ref18","article-title":"Anytime PSRO for two-player zero-sum games","author":"McAleer","year":"2022","journal-title":"arXiv:2201.07700"},{"key":"ref19","article-title":"Fusion-PSRO: Nash policy fusion for policy space response oracles","author":"Lian","year":"2024","journal-title":"arXiv:2405.21027"},{"key":"ref20","first-page":"434","article-title":"Open-ended learning in symmetric zero-sum games","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Balduzzi"},{"key":"ref21","article-title":"Discovering diverse multi-agent strategic behavior via reward randomization","author":"Tang","year":"2021","journal-title":"arXiv:2103.04564"},{"key":"ref22","first-page":"67771","article-title":"Policy space diversity for non-transitive games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yao"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3457509"},{"key":"ref24","article-title":"Conflux-PSRO: Effectively leveraging collective advantages in policy space response oracles","author":"Huang","year":"2024","journal-title":"arXiv:2410.22776"},{"key":"ref25","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":"ref26","first-page":"941","article-title":"Towards unifying behavioral and response diversity for open-ended learning in zero-sum games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref27","first-page":"10339","article-title":"A unified diversity measure for multiagent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Liu"},{"key":"ref28","first-page":"1407","article-title":"IMPALA: Scalable distributed deeP-RL with importance weighted actor-learner architectures","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Espeholt"},{"key":"ref29","article-title":"Distributed prioritized experience replay","author":"Horgan","year":"2018","journal-title":"arXiv:1803.00933"},{"key":"ref30","article-title":"SEED RL: Scalable and efficient deep-RL with accelerated central inference","author":"Espeholt","year":"2019","journal-title":"arXiv:1910.06591"},{"issue":"150","key":"ref31","first-page":"1","article-title":"MALib: A parallel framework for population-based multi-agent reinforcement learning","volume":"24","author":"Zhou","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref32","first-page":"18050","article-title":"Effective diversity in population based reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Parker-Holder"},{"key":"ref33","first-page":"1","article-title":"Disagreement-regularized imitation learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Brantley"},{"key":"ref34","article-title":"A survey on self-play methods in reinforcement learning","author":"Zhang","year":"2024","journal-title":"arXiv:2408.01072"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/880"},{"volume-title":"Game Theory","year":"1991","author":"Fudenberg","key":"ref36"},{"issue":"1","key":"ref37","first-page":"374","article-title":"Iterative solution of games by fictitious play","volume":"13","author":"Brown","year":"1951","journal-title":"Act. Anal. Prod Allocation"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8830"},{"key":"ref39","article-title":"TiKick: Towards playing multi-agent football full games from single-agent demonstrations","author":"Huang","year":"2021","journal-title":"arXiv:2110.04507"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.01955"},{"key":"ref42","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref43","article-title":"TiZero: Mastering multi-agent football with curriculum learning and self-play","author":"Lin","year":"2023","journal-title":"arXiv:2302.07515"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11022714\/10950104.pdf?arnumber=10950104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T17:57:44Z","timestamp":1749059864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10950104\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":43,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3550827","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}