{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:19:32Z","timestamp":1774628372945,"version":"3.50.1"},"reference-count":19,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF Collaborative Research: THEORINET","award":["DMS-2031899"],"award-info":[{"award-number":["DMS-2031899"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lcsys.2024.3510193","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T18:43:49Z","timestamp":1733165029000},"page":"2643-2648","source":"Crossref","is-referenced-by-count":2,"title":["Convergence of Decentralized Actor-Critic Algorithm in General\u2013Sum Markov Games"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3596-2851","authenticated-orcid":false,"given":"Chinmay","family":"Maheshwari","sequence":"first","affiliation":[{"name":"Department of EECS, University of California at Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5334-4163","authenticated-orcid":false,"given":"Manxi","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, University of California at Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1300-1574","authenticated-orcid":false,"given":"Shankar","family":"Sastry","sequence":"additional","affiliation":[{"name":"Department of EECS, University of California at Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Decentralized Q-learning in zero-sum Markov games","volume-title":"Proc. NeurIPS","author":"Sayin"},{"key":"ref2","first-page":"5527","article-title":"Independent policy gradient methods for competitive reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Daskalakis"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2598476"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3121228"},{"key":"ref5","article-title":"Independent and decentralized learning in Markov potential games","author":"Maheshwari","year":"2022","journal-title":"arXiv:2205.14590"},{"key":"ref6","first-page":"4414","article-title":"Independent natural policy gradient always converges in Markov potential games","volume-title":"Proc. AISTATS","author":"Fox"},{"key":"ref7","article-title":"Asynchronous decentralized Q-learning: Two timescale analysis by persistence","author":"Yongacoglu","year":"2023","journal-title":"arXiv:2308.03239"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s13235-021-00420-0"},{"key":"ref9","article-title":"V-learning\u2014A simple, efficient, decentralized algorithm for multiagent RL","author":"Jin","year":"2021","journal-title":"arXiv:2110.14555"},{"issue":"371","key":"ref10","first-page":"1","article-title":"Decentralized robust V-learning for solving Markov games with model uncertainty","volume":"24","author":"Ma","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2465769.2465776"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2013.07.001"},{"key":"ref13","article-title":"An \u03b1-potential game framework for N-player games","author":"Guo","year":"2024","journal-title":"arXiv:2403.16962"},{"key":"ref14","article-title":"Markov \u03b1-potential games","author":"Guo","year":"2023","journal-title":"arXiv:2305.12553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2024.3402132"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1287\/11-SSY056"},{"key":"ref17","article-title":"Decentralized learning in general-sum Markov games","author":"Maheshwari","year":"2024","journal-title":"arXiv:2409.04613"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3982\/te632"},{"key":"ref19","first-page":"5166","article-title":"Independent policy gradient for large-scale Markov potential games: Sharper rates, function approximation, and game-agnostic convergence","volume-title":"Proc. ICML","author":"Ding"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7782633\/10411713\/10772192-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782633\/10411713\/10772192.pdf?arnumber=10772192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T06:53:58Z","timestamp":1734072838000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10772192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/lcsys.2024.3510193","relation":{},"ISSN":["2475-1456"],"issn-type":[{"value":"2475-1456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}