{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:21:18Z","timestamp":1740100878455,"version":"3.37.3"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6,8]]},"DOI":"10.23919\/acc53348.2022.9867152","type":"proceedings-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:24:10Z","timestamp":1662409450000},"page":"3273-3278","source":"Crossref","is-referenced-by-count":5,"title":["Distributed Cooperative Multi-Agent Reinforcement Learning with Directed Coordination Graph"],"prefix":"10.23919","author":[{"given":"Gangshan","family":"Jing","sequence":"first","affiliation":[{"name":"Chongqing University,School of Automation,Chongqing,China,400044"}]},{"given":"He","family":"Bai","sequence":"additional","affiliation":[{"name":"Oklahoma State University,Stillwater,OK,USA,74078"}]},{"given":"Jemin","family":"George","sequence":"additional","affiliation":[{"name":"DEVCOM U.S. Army Research Laboratory,Adelphi,MD,USA,20783"}]},{"given":"Aranya","family":"Chakrabortty","sequence":"additional","affiliation":[{"name":"North Carolina State University,Raleigh,NC,USA,27695"}]},{"given":"Piyush. K.","family":"Sharma","sequence":"additional","affiliation":[{"name":"DEVCOM U.S. Army Research Laboratory,Adelphi,MD,USA,20783"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payoff propagation","volume":"7","author":"kok","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","first-page":"2926","article-title":"Contrasting exploration in parameter and action space: A zeroth-order optimization perspective","author":"vemula","year":"2019","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"article-title":"Zeroth-order deterministic policy gradient","year":"2020","author":"kumar","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/ACC53348.2022.9867152"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"article-title":"Improving the convergence rate of one-point zeroth-order optimization using residual feedback","year":"2020","author":"zhang","key":"ref15"},{"key":"ref4","article-title":"Communication-efficient policy gradient methods for distributed reinforcement learning","author":"chen","year":"2021","journal-title":"IEEE Transactions on Control of Network Systems"},{"article-title":"Cooperative multi-agent reinforcement learning with partial observations","year":"2020","author":"zhang","key":"ref3"},{"key":"ref6","first-page":"1","article-title":"Multi-agent deep reinforcement learning: a survey","author":"gronauer","year":"2021","journal-title":"Artificial Intelligence Review"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2995814"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref7","first-page":"256","article-title":"Scalable reinforcement learning of localized policies for multi-agent networked systems","author":"qu","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref2","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref9","first-page":"227","article-title":"Coordinated reinforcement learning","volume":"2","author":"guestrin","year":"2002","journal-title":"ICML"}],"event":{"name":"2022 American Control Conference (ACC)","start":{"date-parts":[[2022,6,8]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2022,6,10]]}},"container-title":["2022 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9866948\/9867142\/09867152.pdf?arnumber=9867152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T20:39:22Z","timestamp":1664829562000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9867152\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,8]]},"references-count":15,"URL":"https:\/\/doi.org\/10.23919\/acc53348.2022.9867152","relation":{},"subject":[],"published":{"date-parts":[[2022,6,8]]}}}