{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T08:07:10Z","timestamp":1769933230312,"version":"3.49.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Foundation CAREER Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/lra.2020.2978451","type":"journal-article","created":{"date-parts":[[2020,3,4]],"date-time":"2020-03-04T21:08:08Z","timestamp":1583356088000},"page":"3967-3974","source":"Crossref","is-referenced-by-count":33,"title":["Reinforcement Learning for POMDP: Partitioned Rollout and Policy Iteration With Application to Autonomous Sequential Repair Problems"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2288-8808","authenticated-orcid":false,"given":"Sushmita","family":"Bhattacharya","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3781-0192","authenticated-orcid":false,"given":"Sahil","family":"Badyal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Wheeler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3964-2049","authenticated-orcid":false,"given":"Stephanie","family":"Gil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6909-7208","authenticated-orcid":false,"given":"Dimitri","family":"Bertsekas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05816-6_18"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7140035"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aar7650"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105157"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915587723"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/0278364908098456"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.003"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918770733"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915619772"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref10","article-title":"Discretized approximations for POMDP with average cost","author":"yu","year":"2012","journal-title":"arXiv 1207 4154 [cs AI]"},{"key":"ref40","first-page":"1772","article-title":"DESPOT: Online POMDP planning with regularization","author":"somani","year":"0","journal-title":"Proc Advances NeurIPS 26"},{"key":"ref11","author":"bertsekas","year":"2019","journal-title":"Optimal Control Based on Reinforcement Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref13","article-title":"A function approximation approach to estimation of policy gradient for POMDP with structured policies","author":"yu","year":"2012","journal-title":"arXiv 1207 1421 [cs LG]"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/nav.21481"},{"key":"ref15","first-page":"1068","article-title":"On-line policy improvement using monte-carlo search","author":"tesauro","year":"0","journal-title":"Proc Adv NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref17","first-page":"424","article-title":"Reinforcement learning as classification: Leveraging modern classifiers","author":"lagoudakis","year":"0","journal-title":"Proc 20th Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-008-5069-3"},{"key":"ref19","first-page":"607","article-title":"Analysis of a classification-based policy iteration algorithm","author":"lazaric","year":"0","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref28","first-page":"17","article-title":"A survey of POMDP applications","author":"cassandra","year":"0","journal-title":"Proc Working Notes AAAI Fall Symp Planning POMDP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/EST.2010.31"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-012-9200-2"},{"key":"ref6","article-title":"Solving POMDPs by searching the space of finite policies","author":"meuleau","year":"2013","journal-title":"arXiv 1301 6720 [cs AI]"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/2041304110394727"},{"key":"ref5","first-page":"211","article-title":"Solving POMDPs by searching in policy space","author":"hansen","year":"0","journal-title":"Proc 14th Conf Uncertainty Artif Intell"},{"key":"ref8","first-page":"2164","article-title":"Monte-carlo planning in large POMDPs","author":"silver","year":"0","journal-title":"Proc 23rd Int Conf NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2567"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1659"},{"key":"ref9","first-page":"707","article-title":"An improved grid-based approximation algorithm for POMDPs","author":"zhou","year":"0","journal-title":"Proc 17th Int Joint Conf Artif Intell"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2078"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2010.5707073"},{"key":"ref21","author":"silver","year":"2017","journal-title":"arXiv 1712 01815v1 [cs AI]"},{"key":"ref42","article-title":"Active rendezvous for multi-robot pose graph optimization using sensing over Wi-Fi","author":"wang","year":"0","journal-title":"arXiv 1907 05538 [cs RO]"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-012-1128-z"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914567793"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1110.0532"},{"key":"ref26","author":"bertsekas","year":"2018","journal-title":"Abstract Dynamic Programming"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386226"},{"key":"ref25","volume":"2","author":"bertsekas","year":"2012","journal-title":"Dynamic Programming and Optimal Control"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9059055\/09024010.pdf?arnumber=9024010","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:33:13Z","timestamp":1651080793000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9024010\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":43,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.2978451","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7]]}}}