{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:36:47Z","timestamp":1768257407263,"version":"3.49.0"},"reference-count":22,"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\/ieeeconf53345.2021.9723200","type":"proceedings-article","created":{"date-parts":[[2022,3,4]],"date-time":"2022-03-04T20:26:46Z","timestamp":1646425606000},"page":"504-508","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Agent Off-Policy TDC with Near-Optimal Sample and Communication Complexity"],"prefix":"10.1109","author":[{"given":"Ziyi","family":"Chen","sequence":"first","affiliation":[{"name":"University of Utah,Department of ECE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Utah,Department of ECE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongrong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Utah,Department of ECE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"10 634","article-title":"Two time-scale off-policy td learning: Non-asymptotic analysis over markovian samples","author":"xu","year":"2019","journal-title":"Proc Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref11","first-page":"4704","article-title":"Finite-time performance bounds and adaptive learning rate selection for two time-scale reinforcement learning","volume":"32","author":"gupta","year":"2019","journal-title":"Proc Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref12","first-page":"2144","article-title":"Finite time analysis of linear two-timescale stochastic approximation with markovian noise","author":"kaledin","year":"2020","journal-title":"In Proceedings of the Conference on Computational Learning Theory (COLT)"},{"key":"ref13","first-page":"9672","article-title":"Multi-agent reinforcement learning via double averaging primal-dual optimization","author":"wai","year":"2018","journal-title":"Proc Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref14","first-page":"1626","article-title":"Finite-time analysis of distributed TD(0) with linear function approximation on multi-agent reinforcement learning","volume":"97","author":"doan","year":"2019","journal-title":"Proc International Conference on Machine Learning (ICML)"},{"key":"ref15","first-page":"4485","article-title":"Finite-sample analysis of decentralized temporal-difference learning with linear function approximation","author":"sun","year":"2020","journal-title":"Proc International Conference on Artificial Intelligence and Statistics (AISTATS)"},{"key":"ref16","article-title":"Decentralized td tracking with linear function approximation and its finite-time analysis","volume":"33","author":"wang","year":"2020","journal-title":"Proc Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2368731"},{"key":"ref18","first-page":"167","article-title":"Multi-agent temporal-difference learning with linear function approximation: Weak convergence under time-varying network topologies","author":"stankovi?","year":"2016","journal-title":"Proc American Control Conference (ACC)"},{"key":"ref19","article-title":"Multi-agent fully decentralized value function learning with linear convergence rates","author":"cassano","year":"2020","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref4","first-page":"1691","article-title":"A finite time analysis of temporal difference learning with linear function approximation","volume":"75","author":"bhandari","year":"2018","journal-title":"In Proceedings of the Conference on Computational Learning Theory (COLT)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992701"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref5","first-page":"8665","article-title":"Finite-sample analysis for sarsa with linear function approximation","author":"zou","year":"2019","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref7","first-page":"1609","article-title":"A convergent o(n) algorithm for off-policy temporal-difference learning with linear function approximation","volume":"21","author":"sutton","year":"2008","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref2","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref9","article-title":"Gradient temporal-difference learning algorithms","author":"maei","year":"2011","journal-title":"Ph D Dissertation"},{"key":"ref20","first-page":"3027","article-title":"Optimal algorithms for smooth and strongly convex distributed optimization in networks","volume":"70","author":"scaman","year":"2017","journal-title":"Proc International Conference on Machine Learning (ICML)"},{"key":"ref22","article-title":"Sample complexity bounds for two timescale value-based reinforcement learning algorithms","author":"xu","year":"2020"},{"key":"ref21","article-title":"Reanalysis of variance reduced temporal difference learning","author":"xu","year":"2020","journal-title":"Proc International Conference on Learning Representations (ICLR)"}],"event":{"name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","location":"Pacific Grove, CA, USA","start":{"date-parts":[[2021,10,31]]},"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\/09723200.pdf?arnumber=9723200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,15]],"date-time":"2022-06-15T20:16:20Z","timestamp":1655324180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9723200\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,31]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf53345.2021.9723200","relation":{},"subject":[],"published":{"date-parts":[[2021,10,31]]}}}