{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T15:19:23Z","timestamp":1761664763927,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","award":["NRF-2021R1I1A3058581"],"award-info":[{"award-number":["NRF-2021R1I1A3058581"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,18]]},"DOI":"10.1109\/icca62789.2024.10591854","type":"proceedings-article","created":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T17:19:13Z","timestamp":1721927953000},"page":"960-967","source":"Crossref","is-referenced-by-count":1,"title":["Continuous-Time Distributed Dynamic Programming for Networked Multi-Agent Markov Decision Processes"],"prefix":"10.1109","author":[{"given":"Donghwan","family":"Lee","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Department of Electrical and Engineering,Daejeon,South Korea,34141"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han-Dong","family":"Lim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Department of Electrical and Engineering,Daejeon,South Korea,34141"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Do Wan","family":"Kim","sequence":"additional","affiliation":[{"name":"Hanbat National University,Department of Electrical Engineering,Daejeon,South Korea,34158"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref2","first-page":"331","article-title":"Markov decision processes","volume-title":"Handbooks in operations research and management science","volume":"2","author":"Puterman","year":"1990"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2976000"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.812781"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-009-9522-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2041686"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/14096668X"},{"volume-title":"Neuro-dynamic programming","year":"1996","author":"Bertsekas","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2010.5706956"},{"key":"ref11","article-title":"Nonlinear systems third edition","volume":"115","author":"Khalil","year":"2002","journal-title":"Patience Hall"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2368731"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7524910"},{"key":"ref14","article-title":"Asynchronous policy evaluation in distributed reinforcement learning over networks","author":"Sha","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"1626","article-title":"Finite-time analysis of distributed TD(0) with linear function approximation on multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Doan","year":"2019"},{"key":"ref16","first-page":"9649","article-title":"Multi-agent reinforcement learning via double averaging primal-dual optimization","author":"Wai","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2995814"},{"key":"ref18","article-title":"Fast multi-agent temporal-difference learning via homotopy stochastic primal-dual optimization","author":"Ding","year":"2019","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303966"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3211395"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-4285-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022633531479"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"key":"ref25","volume-title":"Stochastic approximation and recursive algorithms and applications","volume":"35","author":"Kushner","year":"2003"},{"key":"ref26","article-title":"A unified switching system perspective and convergence analysis of Q-learning algorithms","volume-title":"34th Conference on Neural Information Processing Systems, NeurIPS 2020","author":"Lee","year":"2020"},{"key":"ref27","article-title":"A discrete-time switching system analysis of Q-learning","author":"Lee","year":"2022","journal-title":"SIAM Journal on Control and Optimization (accepted)"}],"event":{"name":"2024 IEEE 18th International Conference on Control &amp; Automation (ICCA)","start":{"date-parts":[[2024,6,18]]},"location":"Reykjav\u00edk, Iceland","end":{"date-parts":[[2024,6,21]]}},"container-title":["2024 IEEE 18th International Conference on Control &amp;amp; Automation (ICCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10591777\/10591797\/10591854.pdf?arnumber=10591854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T05:25:19Z","timestamp":1721971519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10591854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,18]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icca62789.2024.10591854","relation":{},"subject":[],"published":{"date-parts":[[2024,6,18]]}}}