{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T16:51:00Z","timestamp":1790787060682,"version":"4.1.0"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-19-1-0169"],"award-info":[{"award-number":["FA9550-19-1-0169"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1932011"],"award-info":[{"award-number":["CNS-1932011"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tac.2023.3288025","type":"journal-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T17:38:32Z","timestamp":1687282712000},"page":"968-981","source":"Crossref","is-referenced-by-count":27,"title":["Cooperative Multiagent Reinforcement Learning With Partial Observations"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4882-9857","authenticated-orcid":false,"given":"Yan","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering and Material Science, Duke University, Durham, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1748-8228","authenticated-orcid":false,"given":"Michael M.","family":"Zavlanos","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering and Material Science, Duke University, Durham, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref2","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref4","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Omidshafiei","year":"2017"},{"key":"ref5","first-page":"5867","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029969"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.12.182"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.110006"},{"key":"ref10","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Fazel","year":"2018"},{"key":"ref11","first-page":"2916","article-title":"Derivative-free methods for policy optimization: Guarantees for linear quadratic systems","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Malik","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3128592"},{"key":"ref13","first-page":"385","article-title":"Online convex optimization in the bandit setting: Gradient descent without a gradient","volume-title":"Proc. 16th Annu. ACM-SIAM Symp. Discrete Algorithms","author":"Flaxman","year":"2005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2409256"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619333"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cdc.2018.8619044"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3033712"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/ECC54610.2021.9654953"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2023.111328"},{"key":"ref21","first-page":"10706","article-title":"Q-value path decomposition for deep multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2020"},{"key":"ref22","first-page":"4190","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Lanctot","year":"2017"},{"key":"ref23","first-page":"3422","article-title":"Actor-critic policy optimization in partially observable multiagent environments","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Srinivasan","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1134\/S0005117917020035"},{"key":"ref26","first-page":"3603","article-title":"Improve single-point zeroth-order optimization using high-pass and low-pass filters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2022"},{"key":"ref27","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Konda","year":"2000"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/16M1084316"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10416290\/10156885.pdf?arnumber=10156885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T19:48:27Z","timestamp":1735847307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10156885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":29,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tac.2023.3288025","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}