{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:56:55Z","timestamp":1778345815725,"version":"3.51.4"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["NSF-CRII-1755829"],"award-info":[{"award-number":["NSF-CRII-1755829"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Mag."],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/msp.2020.2976000","type":"journal-article","created":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T20:10:53Z","timestamp":1588363853000},"page":"123-135","source":"Crossref","is-referenced-by-count":89,"title":["Optimization for Reinforcement Learning: From a single agent to cooperative agents"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4962-8478","authenticated-orcid":false,"given":"Donghwan","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4225-7536","authenticated-orcid":false,"given":"Niao","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Parameswaran","family":"Kamalaruban","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volkan","family":"Cevher","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2368731"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref33","author":"chen","year":"2016","journal-title":"Stochastic primal-dual methods and sample complexity of reinforcement learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref30","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref37","article-title":"Boosting the actor with dual critic","author":"dai","year":"0","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref36","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref35","author":"lee","year":"2018","journal-title":"Stochastic primal-dual Q-learning"},{"key":"ref34","first-page":"1133","article-title":"SBEED: Convergent reinforcement learning with nonlinear function approximation","author":"dai","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2585302"},{"key":"ref28","first-page":"1458","article-title":"Learning from conditional distributions via dual embeddings","author":"dai","year":"0","journal-title":"Proc Int Conf Artificial Intelligence Statistics"},{"key":"ref27","first-page":"1609","article-title":"A convergent O(n) temporal-difference algorithm for off-policy learning with linear function approximation","author":"sutton","year":"0","journal-title":"Proc Advances Neural Information Processing System Conf"},{"key":"ref29","first-page":"3713","article-title":"Target-based gradient TD-learning","author":"lee","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref2","first-page":"464","article-title":"Multi-agent reinforcement learning in sequential social dilemmas","author":"leibo","year":"0","journal-title":"Proc 16th Conf Autonomous Agents and MultiAgent Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref20","author":"nguyen","year":"2018","journal-title":"Deep reinforcement learning for multi-agent systems A review of challenges solutions and applications"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref24","first-page":"6144","article-title":"Finite sample analyses for TD(0) with function approximation","author":"dalal","year":"0","journal-title":"Proc AAAI Conf Artificial Intelligence"},{"key":"ref23","author":"bhandari","year":"2018","journal-title":"A finite time analysis of temporal difference learning with linear function approximation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref25","first-page":"2803","article-title":"Finite-time error bounds for linear stochastic approximation and TD learning","volume":"99","author":"srikant","year":"0","journal-title":"Proc 32nd Annu Conf Learn Theory"},{"key":"ref50","first-page":"1529","article-title":"Prox-PDA: The proximal primal-dual algorithm for fast distributed nonconvex optimization and learning over networks","author":"hong","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2160394"},{"key":"ref59","author":"fujimoto","year":"2018","journal-title":"Addressing Function Approximation Error in Actor-Critic Methods"},{"key":"ref58","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref57","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref56","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2836919"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2017.2698261"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7524910"},{"key":"ref10","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"0","journal-title":"Proc 15th Nat Conf Artificial Intelligence"},{"key":"ref11","author":"doan","year":"2019","journal-title":"Convergence rates of distributed TD(0) with linear function approximation for multi-agent reinforcement learning"},{"key":"ref40","author":"mahadevan","year":"2014","journal-title":"Proximal reinforcement learning A new theory of sequential decision making in primal-dual spaces"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref13","author":"zhang","year":"2018","journal-title":"Fully decentralized multi-agent reinforcement learning with networked agents"},{"key":"ref14","author":"zhang","year":"2018","journal-title":"Finite-sample analyses for fully decentralized multi-agent reinforcement learning"},{"key":"ref15","author":"qu","year":"2019","journal-title":"Value propagation for decentralized networked deep multi-agent reinforcement learning"},{"key":"ref16","first-page":"9672","article-title":"Multi-agent reinforcement learning via double averaging primal-dual optimization","author":"wai","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref17","author":"lee","year":"2018","journal-title":"Stochastic primal-dual algorithm for distributed gradient temporal difference learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1561\/2600000004"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref4","author":"foerster","year":"2016","journal-title":"Learning to communicate to solve riddles with deep distributed recurrent q-networks"},{"key":"ref3","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume":"70","author":"foerster","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3233\/KES-2010-0206"},{"key":"ref8","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"0","journal-title":"Proc 17th Int Conf Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2167817"},{"key":"ref9","first-page":"1516","article-title":"Reinforcement learning for stochastic cooperative multi-agent systems","volume":"3","author":"lauer","year":"0","journal-title":"Proc 3rd Int Joint Conf Autonomous Agents and Multiagent Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/14096668X"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2041686"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2079650"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2364096"},{"key":"ref42","first-page":"489","article-title":"Learning to cooperate via policy search","author":"peshkin","year":"0","journal-title":"Proc 16th Conf Uncertainty in Artificial Intelligence"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.2991\/agi.2010.22"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.812781"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ISWCS.2008.4726117"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/79\/9084311\/09084325.pdf?arnumber=9084325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:35:53Z","timestamp":1651073753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9084325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":60,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/msp.2020.2976000","relation":{},"ISSN":["1053-5888","1558-0792"],"issn-type":[{"value":"1053-5888","type":"print"},{"value":"1558-0792","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}