{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T04:27:51Z","timestamp":1730262471015,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"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":[[2021,10,31]]},"DOI":"10.1109\/ieeeconf53345.2021.9723192","type":"proceedings-article","created":{"date-parts":[[2022,3,4]],"date-time":"2022-03-04T20:26:46Z","timestamp":1646425606000},"page":"1023-1026","source":"Crossref","is-referenced-by-count":0,"title":["Randomized Linear Programming for Tabular Average-Cost Multi-agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Alec","family":"Koppel","sequence":"first","affiliation":[{"name":"Amazon,Supply Chain Optimization Technologies"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amrit","family":"Singh Bedi","sequence":"additional","affiliation":[{"name":"Amazon,Supply Chain Optimization Technologies"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhargav","family":"Ganguly","sequence":"additional","affiliation":[{"name":"Purdue University,School of Industrial Engineering,West Lafayette,IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vaneet","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"Purdue University,School of Industrial Engineering,West Lafayette,IN"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"11 245","DOI":"10.3182\/20110828-6-IT-1002.01959","article-title":"Decentralized multiagent optimization via dual decomposition","volume":"44","author":"terelius","year":"2011","journal-title":"IFAC Proceedings Volumes"},{"journal-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","year":"2011","author":"boyd","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF01414028"},{"journal-title":"Linear Programming and Finite Markovian Control Problems","year":"1983","author":"kallenberg","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/19M1288012"},{"journal-title":"Scalable multi-agent reinforcement learning for networked systems with average reward","year":"2020","author":"qu","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2449255"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2012.2198470"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2019.1000"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1287\/opre.51.6.850.24925"},{"key":"ref10","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"29","author":"foerster","year":"2016","journal-title":"NeurIPS"},{"journal-title":"Spectral Graph Theory","year":"1997","author":"chung","key":"ref40"},{"key":"ref11","first-page":"464","article-title":"Multi-agent reinforcement learning in sequential social dilemmas","volume":"16","author":"leibo","year":"2017","journal-title":"AAMAS"},{"key":"ref12","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"Proceedings of the 34th in ICML-Volume 70"},{"key":"ref13","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"ICML"},{"article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","year":"1998","author":"claus","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2976000"},{"journal-title":"Stochastic primal-dual algorithm for distributed gradient temporal difference learning","year":"2018","author":"lee","key":"ref16"},{"key":"ref17","first-page":"1626","article-title":"Finite-time analysis of distributed td (0) with linear function approximation on multiagent reinforcement learning","author":"doan","year":"2019","journal-title":"ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref19","first-page":"9649","article-title":"Multi-agent reinforcement learning via double averaging primal-dual optimization","author":"wai","year":"2018","journal-title":"NeurIPS"},{"journal-title":"Fully asynchronous policy evaluation in distributed reinforcement learning over networks","year":"2020","author":"sha","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10614-020-10038-w"},{"journal-title":"Distributed reinforcement learning in multi-agent networked systems","year":"2020","author":"lin","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015504423309"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303966"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-014-1652-0"},{"journal-title":"Dynamic Noncooperative Game Theory","year":"1998","author":"ba?ar","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781316471104"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"ref20","first-page":"1184","article-title":"Value propagation for decentralized networked deep multi-agent reinforcement learning","author":"qu","year":"2019","journal-title":"NeurIPS"},{"key":"ref22","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"ICML"},{"key":"ref21","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1287\/opre.51.6.850.24925"},{"journal-title":"Correcting experience replay for multiagent communication","year":"2020","author":"ahilan","key":"ref24"},{"key":"ref41","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref23","first-page":"13 111","article-title":"Biases for emergent communication in multi-agent reinforcement learning","author":"eccles","year":"2019","journal-title":"NeurIPS"},{"key":"ref26","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"},{"journal-title":"Convergence rates of average-reward multi-agent reinforcement learning via randomized linear programming","year":"2021","author":"koppel","key":"ref43"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103356"}],"event":{"name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","start":{"date-parts":[[2021,10,31]]},"location":"Pacific Grove, CA, USA","end":{"date-parts":[[2021,11,3]]}},"container-title":["2021 55th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9723034\/9723086\/09723192.pdf?arnumber=9723192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,15]],"date-time":"2022-06-15T20:16:50Z","timestamp":1655324210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9723192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,31]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf53345.2021.9723192","relation":{},"subject":[],"published":{"date-parts":[[2021,10,31]]}}}