{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:28:13Z","timestamp":1771025293213,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1 509 040"],"award-info":[{"award-number":["1 509 040"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1 508 993"],"award-info":[{"award-number":["1 508 993"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1 711 471"],"award-info":[{"award-number":["1 711 471"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-17-2-0196"],"award-info":[{"award-number":["W911NF-17-2-0196"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Rensselaer-IBM AI Research Collaboration"},{"name":"IBM AI Horizons Network"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Control Netw. Syst."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/tcns.2021.3078100","type":"journal-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T19:49:49Z","timestamp":1620330589000},"page":"917-929","source":"Crossref","is-referenced-by-count":54,"title":["Communication-Efficient Policy Gradient Methods for Distributed Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3477-1439","authenticated-orcid":false,"given":"Tianyi","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7446-7581","authenticated-orcid":false,"given":"Kaiqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0196-0260","authenticated-orcid":false,"given":"Georgios B.","family":"Giannakis","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Digital Technology Center, University of Minnesota, Minneapolis, MN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4406-7875","authenticated-orcid":false,"given":"Tamer","family":"Basar","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/301136.301167"},{"key":"ref32","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"0","journal-title":"Proc Assoc Adv Artif Intell"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref30","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref37","first-page":"66","article-title":"Cooperative multi-agent control using deep reinforcement learning","author":"gupta","year":"0","journal-title":"Proc Int Conf Auton Agents Multi-Agent Syst"},{"key":"ref36","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","first-page":"371","article-title":"Distributed value functions","author":"schneider","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","first-page":"671","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","author":"boyan","year":"0","journal-title":"Proc Adv Neural Inf"},{"key":"ref28","first-page":"3591","article-title":"Adaptive batch size for safe policy gradients","author":"papini","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","first-page":"i-387?i-395","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","article-title":"Communication-efficient distributed statistical inference","author":"jordan","year":"2018","journal-title":"J Amer Stat Assoc"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"},{"key":"ref21","article-title":"LAG: Lazily aggregated gradient for communication-efficient distributed learning","author":"chen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3029317"},{"key":"ref25","first-page":"4026","article-title":"Stochastic variance-reduced policy gradient","author":"papini","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2239000"},{"key":"ref51","article-title":"Communication-efficient distributed reinforcement learning","author":"chen","year":"2018"},{"key":"ref56","article-title":"OpenAI Gym","author":"brockman","year":"2016"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1137\/19M1288012"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116037"},{"key":"ref53","first-page":"2635","article-title":"Learnability, stability and uniform convergence","volume":"11","author":"shalev-shwartz","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref52","author":"vapnik","year":"2013","journal-title":"The Nature of Statistical Learning Theory"},{"key":"ref10","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","article-title":"Massively parallel methods for deep reinforcement learning","author":"nair","year":"2015"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29946-9_30"},{"key":"ref12","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","first-page":"583","article-title":"Scaling distributed machine learning with the parameter server","author":"li","year":"0","journal-title":"Proc USENIX Symp Operat Syst Des Implement"},{"key":"ref15","article-title":"Federated learning: Collaborative machine learning without centralized training data","author":"mcmahan","year":"2017","journal-title":"Google Research Blog"},{"key":"ref16","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref17","article-title":"A Berkeley view of systems challenges for AI","author":"stoica","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2839563"},{"key":"ref19","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","author":"alistarh","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008942012299"},{"key":"ref5","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref7","article-title":"Multiagent cooperation and competition with deep reinforcement learning","author":"tampuu","year":"2015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref9","article-title":"Multi-agent reinforcement learning via double averaging primal-dual optimization","author":"wai","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","volume":"9","author":"deisenroth","year":"2010","journal-title":"Efficient Reinforcement Learning Using Gaussian Processes"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264668"},{"key":"ref48","article-title":"Massively parallel methods for deep reinforcement learning","author":"nair","year":"0","journal-title":"Proc Int Conf Mach Learn Deep Learn Workshop"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-9707-1_16"},{"key":"ref42","article-title":"Local SGD converges fast and communicates little","author":"stich","year":"2018"},{"key":"ref41","first-page":"362","article-title":"DiSCO: Distributed optimization for self-concordant empirical loss","author":"zhang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.03.009"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2174666"}],"container-title":["IEEE Transactions on Control of Network Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6509490\/9800706\/9424975-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6509490\/9800706\/09424975.pdf?arnumber=9424975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T20:34:27Z","timestamp":1658176467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9424975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":56,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcns.2021.3078100","relation":{},"ISSN":["2325-5870","2372-2533"],"issn-type":[{"value":"2325-5870","type":"electronic"},{"value":"2372-2533","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}