{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:22:34Z","timestamp":1730204554881,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9682939","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:50:18Z","timestamp":1643748618000},"page":"2613-2620","source":"Crossref","is-referenced-by-count":0,"title":["Intermittent Communications in Decentralized Shadow Reward Actor-Critic"],"prefix":"10.1109","author":[{"given":"Amrit Singh","family":"Bedi","sequence":"first","affiliation":[{"name":"U.S. Army Research Laboratory,Adelphi,MD,USA,20783"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alec","family":"Koppel","sequence":"additional","affiliation":[{"name":"U.S. Army Research Laboratory,Adelphi,MD,USA,20783"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengdi","family":"Wang","sequence":"additional","affiliation":[{"name":"Princeton University,Dept. of Electrical Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Princeton University,Dept. of Electrical Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref32","first-page":"641","article-title":"Decomposition by partial linearization: Parallel optimization of multi-agent systems","volume":"62","author":"scutari","year":"2013","journal-title":"IEEE TSP"},{"key":"ref31","first-page":"1626","article-title":"Finite-time analysis of distributed td (0) with linear function approximation on multi-agent reinforcement learning","author":"doan","year":"2019","journal-title":"ICML"},{"key":"ref30","first-page":"1184","article-title":"Value propagation for decentralized networked deep multi-agent reinforcement learning","author":"qu","year":"2019","journal-title":"NeurIPS"},{"key":"ref35","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973433"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971132"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref12","first-page":"2681","article-title":"Provably efficient maximum entropy exploration","author":"hazan","year":"2019","journal-title":"ICML"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.1.192.334"},{"key":"ref14","volume":"7","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF01414028"},{"key":"ref17","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Variational policy gradient method for reinforcement learning with general utilities","volume":"33","author":"zhang","year":"2020","journal-title":"NeurIPS"},{"article-title":"Marl with general utilities via decentralized shadow reward actor-critic","year":"2021","author":"zhang","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"article-title":"Cautious reinforcement learning via distributional risk in the dual domain","year":"2020","author":"zhang","key":"ref27"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2016.0145"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"ref29","first-page":"9649","article-title":"Multi-agent reinforcement learning via double averaging primal-dual optimization","author":"wai","year":"2018","journal-title":"NeurIPS"},{"key":"ref8","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in starcraft ii using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref2","first-page":"102","article-title":"Contributions to the theory of optimal control","volume":"5","author":"kalman","year":"1960","journal-title":"Bol Soc Mat Mexicana"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.874516"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2007.895948"},{"journal-title":"Spectral Graph Theory","year":"1997","author":"chung","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2449255"},{"article-title":"Communication-efficient distributed reinforcement learning","year":"2018","author":"chen","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.03.009"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2021,12,14]]},"location":"Austin, TX, USA","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09682939.pdf?arnumber=9682939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T23:40:21Z","timestamp":1670283621000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9682939\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9682939","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}