{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T01:16:17Z","timestamp":1793754977017,"version":"4.6.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ONR Young Investigators","award":["N00014-21-1-2714"],"award-info":[{"award-number":["N00014-21-1-2714"]}]},{"name":"Sloan Research Fellowship","award":["FG-2020-13998"],"award-info":[{"award-number":["FG-2020-13998"]}]},{"name":"NSF","award":["2114733"],"award-info":[{"award-number":["2114733"]}]},{"name":"Apple Scholars in AI\/ML Ph.D. Fellowship Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tro.2023.3347128","type":"journal-article","created":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T14:44:03Z","timestamp":1703601843000},"page":"2003-2023","source":"Crossref","is-referenced-by-count":16,"title":["Multiagent Reinforcement Learning: Rollout and Policy Iteration for POMDP With Application to Multirobot Problems"],"prefix":"10.1109","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2288-8808","authenticated-orcid":false,"given":"Sushmita","family":"Bhattacharya","sequence":"first","affiliation":[{"name":"REACT Lab, Computer Science Department, School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9247-8882","authenticated-orcid":false,"given":"Siva","family":"Kailas","sequence":"additional","affiliation":[{"name":"REACT Lab, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3781-0192","authenticated-orcid":false,"given":"Sahil","family":"Badyal","sequence":"additional","affiliation":[{"name":"REACT Lab, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4951-5350","authenticated-orcid":false,"given":"Stephanie","family":"Gil","sequence":"additional","affiliation":[{"name":"REACT Lab, Computer Science Department, School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6909-7208","authenticated-orcid":false,"given":"Dimitri","family":"Bertsekas","sequence":"additional","affiliation":[{"name":"Department of Computer, Information, and Decision Systems Engineering, Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2164","article-title":"Monte-Carlo planning in large POMDPs","volume-title":"Proc. 23rd Int. Conf. NeurIPS","author":"Silver","year":"2010"},{"key":"ref2","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1003814"},{"key":"ref4","volume-title":"Rollout, Policy Iteration, and Distributed Reinforcement Learning","author":"Bertsekas","year":"2020"},{"key":"ref5","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas","year":"2019"},{"key":"ref6","volume-title":"Lessons From Alphazero for Optimal, Model Predictive, and Adaptive Control","author":"Bertsekas","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17412"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.01.079"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2978451"},{"key":"ref10","first-page":"1814","article-title":"Multiagent rollout and policy iteration for POMDP with application to multi-robot repair problems","volume-title":"Proc. Conf. Robot Learn.","author":"Bhattacharya","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref12","article-title":"Solving POMDPs by searching the space of finite policies","volume-title":"Proc. 15th Conf. Uncertainty Artif. Intell.","author":"Meuleau","year":"1999"},{"key":"ref13","first-page":"707","article-title":"An improved grid-based approximation algorithm for POMDPs","volume-title":"Proc. 17th Int. Joint Conf. Artif. Intell.","author":"Zhou","year":"2001"},{"key":"ref14","first-page":"619","article-title":"Discretized approximations for POMDP with average cost","volume-title":"Proc. 20th Conf. Uncertainty Artif. Intell.","author":"Yu","year":"2004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref16","first-page":"642","article-title":"A function approximation approach to estimation of policy gradient for POMDP with structured policies","volume-title":"Proc. 21st Conf. Uncertainty Artif. Intell.","author":"Yu","year":"2005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/nav.21481"},{"key":"ref18","first-page":"1772","article-title":"DESPOT: Online POMDP planning with regularization","volume-title":"Proc. Adv. NeurIPS","author":"Somani","year":"2013"},{"key":"ref19","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913483345"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793777"},{"key":"ref24","first-page":"13597","article-title":"Neurosymbolic transformers for multi-agent communication","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Inala","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/EST.2010.31"},{"key":"ref27","first-page":"17","article-title":"A survey of POMDP applications","volume-title":"Proc. Work. Notes AAAI Fall Symp. Plan. Partially Observable Markov Decis. Processes","author":"Cassandra","year":"1998"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/0278364908098456"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09467-6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030241"},{"key":"ref32","first-page":"424","article-title":"Reinforcement learning as classification: Leveraging modern classifiers","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"Lagoudakis","year":"2003"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-008-5069-3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9348131"},{"key":"ref35","volume-title":"Introduction to probability","author":"Bertsekas","year":"2000"},{"key":"ref36","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas","year":"2019"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8860\/10365208\/10374262-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8860\/10365208\/10374262.pdf?arnumber=10374262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T14:00:51Z","timestamp":1738677651000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10374262\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/tro.2023.3347128","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}