{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:21:59Z","timestamp":1730204519961,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["ECCS2038416,EPCN1608361,EARS1516075,CNS1955777,CCF2008130,CMMI2240981,EARS1516075,CNS1955777,CCF2008130,CMMI2240981"],"award-info":[{"award-number":["ECCS2038416,EPCN1608361,EARS1516075,CNS1955777,CCF2008130,CMMI2240981,EARS1516075,CNS1955777,CCF2008130,CMMI2240981"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10383989","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"5410-5415","source":"Crossref","is-referenced-by-count":0,"title":["A Strong Duality Result for Cooperative Decentralized Constrained POMDPs"],"prefix":"10.1109","author":[{"given":"Nouman","family":"Khan","sequence":"first","affiliation":[{"name":"University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,MI,48109-2122"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vijay","family":"Subramanian","sequence":"additional","affiliation":[{"name":"University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,MI,48109-2122"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(65)90154-X"},{"volume-title":"Dynamic Programming and Markov Processes","year":"1960","author":"Howard","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.5.1071"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1287\/opre.26.2.282"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1287\/moor.19.1.169"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF01303434"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF01435458"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1287\/moor.21.4.922"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1287\/moor.21.4.922"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/moor.25.1.130.15210"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.108582"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/pen.21907"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.08.007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2010.08.013"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-012-9989-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20302"},{"key":"ref21","first-page":"3274","article-title":"Triple-Q: A model-free algorithm for constrained reinforcement learning with sublinear regret and zero constraint violation","volume-title":"AISTATS","volume":"151","author":"Wei"},{"volume-title":"DOPE: Doubly optimistic and pessimistic exploration for safe reinforcement learning","year":"2021","author":"Bura","key":"ref22"},{"key":"ref23","article-title":"Near-optimal sample complexity bounds for constrained MDPs","volume-title":"NeurIPS","author":"Vaswani","year":"2022"},{"key":"ref24","first-page":"1968","article-title":"Point-Based Value Iteration for Constrained POMDPs","volume-title":"IJCAI","author":"Kim","year":"2011"},{"key":"ref25","article-title":"Monte-Carlo tree search for constrained POMDPs","volume-title":"NeurIPS","volume":"31","author":"Lee","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509743"},{"volume-title":"Online planning for constrained POMDPs with continuous spaces through dual ascent","year":"2022","author":"Jamgochian","key":"ref27"},{"key":"ref28","first-page":"32","article-title":"The complexity of decentralized control of markov decision processes","author":"Bernstein","year":"2000","journal-title":"UAI"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1979.tb02263.x"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF01824800"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2239000"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02150-8_4"},{"key":"ref33","first-page":"6947","article-title":"Common information based approximate state representations in multi-agent reinforcement learning","volume-title":"AISTATS","volume":"151","author":"Kao"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref35","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"NeurIPS","volume":"33","author":"Rashid","year":"2020"},{"key":"ref36","first-page":"208","article-title":"Mesures dans les espaces produits","volume":"7","author":"Tulcea","year":"1949","journal-title":"Lincei-Rend.Sc. fis. mat. e nat."},{"volume-title":"A Strong Duality Result for Constrained POMDPs with Multiple Cooperative Agents","year":"2023","author":"Khan","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-4015-8"},{"volume-title":"Cooperative Multi-Agent Constrained Pomdps: Strong Duality and Primal-Dual Reinforcement Learning with Approximate Information States","year":"2023","author":"Khan","key":"ref39"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10383989.pdf?arnumber=10383989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:33:04Z","timestamp":1706027584000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10383989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10383989","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}