{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:30:33Z","timestamp":1759332633645,"version":"3.28.0"},"reference-count":30,"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\/cdc45484.2021.9683385","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:50:18Z","timestamp":1643748618000},"page":"5932-5939","source":"Crossref","is-referenced-by-count":2,"title":["Scalable Planning in Multi-Agent MDPs"],"prefix":"10.1109","author":[{"given":"Dinuka","family":"Sahabandu","sequence":"first","affiliation":[{"name":"University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195-2500"}]},{"given":"Luyao","family":"Niu","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute,Department of Electrical and Computer Engineering,Worcester,MA,USA,01609"}]},{"given":"Andrew","family":"Clark","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute,Department of Electrical and Computer Engineering,Worcester,MA,USA,01609"}]},{"given":"Radha","family":"Poovendran","sequence":"additional","affiliation":[{"name":"University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195-2500"}]}],"member":"263","reference":[{"key":"ref30","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref10","first-page":"302","article-title":"Decentralized Markov decision processes with event-driven interactions","author":"becker","year":"2004","journal-title":"Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems-Volume 1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1082473.1082619"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016054"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760239"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11418"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029635"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0121195"},{"key":"ref17","first-page":"1202","article-title":"Online submodular maximization with preemption","author":"buchbinder","year":"2014","journal-title":"Proceedings of the Twenty-Sixth Annual ACM-SIAM Symposium on Discrete Algorithms"},{"key":"ref18","first-page":"427","article-title":"Adaptive submodularity: Theory and applications in active learning and stochastic optimization","volume":"42","author":"golovin","year":"2011","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623637"},{"key":"ref28","article-title":"Event-detecting multi-agent mdps: Complexity and constant-factor approximation","author":"kumar","year":"2009","journal-title":"Twenty-First International Joint Conference on Artificial Intelligence"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1497"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/0278364908099853"},{"key":"ref3","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"Proc Seventh Int Conf Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"article-title":"Markov decision process (MDP) toolbox for Python","year":"2015","author":"cordwell","key":"ref29"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10709","article-title":"Decentralized planning in stochastic environments with submodular rewards","author":"kumar","year":"2017","journal-title":"Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence"},{"article-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms","year":"2019","author":"zhang","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015575522401"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-0417(01)00015-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1000"},{"key":"ref1","first-page":"1603","article-title":"Reinforcement learning to play an optimal Nash equilibrium in team Markov games","author":"wang","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"3356","article-title":"Exploiting submodular value functions for faster dynamic sensor selection","author":"satsangi","year":"2015","journal-title":"Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence"},{"key":"ref22","volume":"39","author":"sch\u00fctze","year":"2008","journal-title":"Introduction to Information Retrieval"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1287\/opre.27.5.1041"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/1017044"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/107"},{"journal-title":"Submodular Functions and Optimization","year":"2005","author":"fujishige","key":"ref26"},{"key":"ref25","first-page":"121","article-title":"Sensitivity analysis, ergodicity coefficients, and rank—one updates","volume":"8","author":"seneta","year":"1991","journal-title":"Numerical Solution of Markov Chains"}],"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\/09683385.pdf?arnumber=9683385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T19:06:11Z","timestamp":1726599971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683385\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683385","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}