{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T01:27:42Z","timestamp":1780536462486,"version":"3.54.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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","award":["12125207"],"award-info":[{"award-number":["12125207"]}],"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":[[2025,2]]},"DOI":"10.1109\/tnnls.2024.3351631","type":"journal-article","created":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T20:49:27Z","timestamp":1706042967000},"page":"2747-2761","source":"Crossref","is-referenced-by-count":17,"title":["Deep Reinforcement Learning for Nash Equilibrium of Differential Games"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7249-962X","authenticated-orcid":false,"given":"Zhenyu","family":"Li","sequence":"first","affiliation":[{"name":"College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0827-7736","authenticated-orcid":false,"given":"Yazhong","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11902-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-26646-2"},{"key":"ref3","volume-title":"Differential Games","author":"Isaacs","year":"1965"},{"key":"ref4","volume-title":"Applied Optimal Control","author":"Bryson","year":"1975"},{"key":"ref5","volume-title":"Dynamic Noncooperative Game Theory","author":"Basar","year":"1995"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11590-017-1197-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/mtits.2017.8005728"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1662-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.12.045"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.04.012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2846048"},{"key":"ref12","volume-title":"Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles","volume":"81","author":"Vrabie","year":"2013"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28070-2_10"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2514\/1.37962"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2021.3075501"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3098985"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213566"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","article-title":"Continuous control with deep reinforcement learning","volume-title":"Int. Conf. Learn. Represent","author":"Lillicrap"},{"key":"ref21","article-title":"Distributed distributional deterministic policy gradients","author":"Barth-Maron","year":"2018","journal-title":"arXiv:1804.08617"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref23","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref24","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"Vinyals","year":"2017","journal-title":"arXiv:1708.04782"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3002852"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/C-CODE.2019.8681003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012904439301"},{"key":"ref28","first-page":"9","article-title":"Fictitious self-play in extensive-form games","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Heinrich"},{"key":"ref29","article-title":"Deep reinforcement learning from self-play in imperfect-information games","author":"Heinrich","year":"2016","journal-title":"arXiv:1603.01121"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3201133"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183250"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2850763"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3171535"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.07.038"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s40815-016-0284-8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3042331"},{"key":"ref39","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2015"},{"key":"ref40","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Bellemare"},{"key":"ref41","first-page":"1","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31th Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref42","volume-title":"The Contraction Mapping Theorem","author":"Conrad","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0095-8956(92)90030-2"},{"key":"ref44","article-title":"The numerics of GANs","author":"Mescheder","year":"2017","journal-title":"arXiv:1705.10461"},{"key":"ref45","first-page":"1","article-title":"The mechanics of n-player differentiable games","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Balduzzi"},{"key":"ref46","volume-title":"Neuro-Dynamic Programming","author":"Bertsekas","year":"1996"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.2514\/1.G004459"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10877690\/10412678.pdf?arnumber=10412678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T07:10:46Z","timestamp":1738912246000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10412678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":47,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3351631","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}