{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T08:34:15Z","timestamp":1768034055712,"version":"3.49.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100006115","name":"Institute for Research in Fundamental Sciences","doi-asserted-by":"publisher","award":["CS 1402-4-208"],"award-info":[{"award-number":["CS 1402-4-208"]}],"id":[{"id":"10.13039\/501100006115","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":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3387871","type":"journal-article","created":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T17:40:16Z","timestamp":1713807616000},"page":"7372-7381","source":"Crossref","is-referenced-by-count":2,"title":["Expected Policy Gradient for Network Aggregative Markov Games in Continuous Space"],"prefix":"10.1109","volume":"36","author":[{"given":"Alireza Ramezani","family":"Moghaddam","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3781-2163","authenticated-orcid":false,"given":"Hamed","family":"Kebriaei","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.108959"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2015.7402549"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2748105"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2973807"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3171535"},{"key":"ref6","volume-title":"Dynamic Noncooperative Game Theory","volume":"23","author":"Basar","year":"1999"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3090515"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2790005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113761"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996209"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072571"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.4962"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2019.12.017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105548"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619581"},{"issue":"52","key":"ref16","first-page":"1","article-title":"Expected policy gradients for reinforcement learning","volume":"21","author":"Whiteson","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3071017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3209313"},{"key":"ref20","article-title":"Mean field multi-agent reinforcement learning","author":"Yang","year":"2018","journal-title":"arXiv:1802.05438"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3291542"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3186229"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146858"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3234049"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3796-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511791307.017"},{"key":"ref27","first-page":"1","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/17M1112583"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11607"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(97)90015-3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1976.1101342"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1985.1104024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2307\/1911749"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10405"},{"key":"ref35","volume-title":"Neuro-Dynamic Programming","author":"Bertsekas","year":"1996"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-75894-2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-8285-7_10"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10949581\/10506114.pdf?arnumber=10506114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T09:28:02Z","timestamp":1743845282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10506114\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":37,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3387871","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}