{"id":"https://openalex.org/W3006655542","doi":"https://doi.org/10.1109/lra.2020.2978451","title":"Reinforcement Learning for POMDP: Partitioned Rollout and Policy Iteration With Application to Autonomous Sequential Repair Problems","display_name":"Reinforcement Learning for POMDP: Partitioned Rollout and Policy Iteration With Application to Autonomous Sequential Repair Problems","publication_year":2020,"publication_date":"2020-03-04","ids":{"openalex":"https://openalex.org/W3006655542","doi":"https://doi.org/10.1109/lra.2020.2978451","mag":"3006655542"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2020.2978451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2978451","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.04175","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036439406","display_name":"Sushmita Bhattacharya","orcid":"https://orcid.org/0000-0003-2288-8808"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sushmita Bhattacharya","raw_affiliation_strings":["REACT Lab, Arizona State University, Tempe, USA","[REACT Lab, Arizona State University, Tempe, USA]"],"raw_orcid":"https://orcid.org/0000-0003-2288-8808","affiliations":[{"raw_affiliation_string":"REACT Lab, Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"[REACT Lab, Arizona State University, Tempe, USA]","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015646268","display_name":"Sahil Badyal","orcid":"https://orcid.org/0000-0002-3781-0192"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sahil Badyal","raw_affiliation_strings":["REACT Lab, Arizona State University, Tempe, USA","[REACT Lab, Arizona State University, Tempe, USA]"],"raw_orcid":"https://orcid.org/0000-0002-3781-0192","affiliations":[{"raw_affiliation_string":"REACT Lab, Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"[REACT Lab, Arizona State University, Tempe, USA]","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037470251","display_name":"Thomas M. Wheeler","orcid":"https://orcid.org/0000-0001-9746-1521"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Wheeler","raw_affiliation_strings":["REACT Lab, Arizona State University, Tempe, USA","[REACT Lab, Arizona State University, Tempe, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"REACT Lab, Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"[REACT Lab, Arizona State University, Tempe, USA]","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102705342","display_name":"Stephanie Gil","orcid":"https://orcid.org/0000-0002-3964-2049"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephanie Gil","raw_affiliation_strings":["Assistant Professor of Computer Science, Arizona State University, Tempe, USA","REACT Lab, Arizona State University, Tempe, USA","[REACT Lab, Arizona State University, Tempe, USA, Assistant Professor of Computer Science, Arizona State University, Tempe, USA]"],"raw_orcid":"https://orcid.org/0000-0002-3964-2049","affiliations":[{"raw_affiliation_string":"Assistant Professor of Computer Science, Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"REACT Lab, Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"[REACT Lab, Arizona State University, Tempe, USA, Assistant Professor of Computer Science, Arizona State University, Tempe, USA]","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039911471","display_name":"Dimitri P. Bertsekas","orcid":"https://orcid.org/0000-0001-6909-7208"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitri Bertsekas","raw_affiliation_strings":["Fulton Professor of Computational Decision Making, Arizona State University, Tempe, USA","McAfee Professor of Engineering, Massachusetts Institute of Technology, Cambridge, USA","[McAfee Professor of Engineering, Massachusetts Institute of Technology, Cambridge, USA, Fulton Professor of Computational Decision Making, Arizona State University, Tempe, USA]"],"raw_orcid":"https://orcid.org/0000-0001-6909-7208","affiliations":[{"raw_affiliation_string":"Fulton Professor of Computational Decision Making, Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"McAfee Professor of Engineering, Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"[McAfee Professor of Engineering, Massachusetts Institute of Technology, Cambridge, USA, Fulton Professor of Computational Decision Making, Arizona State University, Tempe, USA]","institution_ids":["https://openalex.org/I63966007","https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2602,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61227404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"5","issue":"3","first_page":"3967","last_page":"3974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.835678219795227},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7330222129821777},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6540866494178772},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6088668704032898},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5703381299972534},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5465093851089478},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5277329683303833},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4967346787452698},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.483418345451355},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4766938388347626},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4640098810195923},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41129904985427856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35132431983947754},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27902454137802124},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2390926480293274},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21775147318840027},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2006988823413849},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15022704005241394},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.1223142147064209}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.835678219795227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7330222129821777},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6540866494178772},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6088668704032898},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5703381299972534},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5465093851089478},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5277329683303833},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4967346787452698},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.483418345451355},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4766938388347626},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4640098810195923},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41129904985427856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35132431983947754},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27902454137802124},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2390926480293274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21775147318840027},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2006988823413849},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15022704005241394},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.1223142147064209},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/lra.2020.2978451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2978451","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2002.04175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.04175","pdf_url":"https://arxiv.org/pdf/2002.04175","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3006655542","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2002.04175","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2002.04175","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.04175","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.04175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.04175","pdf_url":"https://arxiv.org/pdf/2002.04175","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3006655542.pdf"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W190675879","https://openalex.org/W1494689917","https://openalex.org/W1506292992","https://openalex.org/W1596538644","https://openalex.org/W1886379263","https://openalex.org/W1938668859","https://openalex.org/W1964782533","https://openalex.org/W1969161726","https://openalex.org/W1997929601","https://openalex.org/W2027855416","https://openalex.org/W2048687352","https://openalex.org/W2055188188","https://openalex.org/W2055228833","https://openalex.org/W2055921164","https://openalex.org/W2096132608","https://openalex.org/W2110962519","https://openalex.org/W2111481694","https://openalex.org/W2124595631","https://openalex.org/W2131490088","https://openalex.org/W2134289401","https://openalex.org/W2135997697","https://openalex.org/W2144446635","https://openalex.org/W2144913588","https://openalex.org/W2148864095","https://openalex.org/W2158907787","https://openalex.org/W2165060096","https://openalex.org/W2167509584","https://openalex.org/W2168359464","https://openalex.org/W2171084228","https://openalex.org/W2227909145","https://openalex.org/W2257979135","https://openalex.org/W2772709170","https://openalex.org/W2783963507","https://openalex.org/W2787690100","https://openalex.org/W2914532759","https://openalex.org/W2952655932","https://openalex.org/W2952748141","https://openalex.org/W2960971247","https://openalex.org/W2963103885","https://openalex.org/W2964248288","https://openalex.org/W2964319688","https://openalex.org/W3099235411","https://openalex.org/W3101822862","https://openalex.org/W3103182070","https://openalex.org/W6607768588","https://openalex.org/W6629836980","https://openalex.org/W6634498526","https://openalex.org/W6635427674","https://openalex.org/W6637465547","https://openalex.org/W6674155736","https://openalex.org/W6678541622","https://openalex.org/W6679703492","https://openalex.org/W6680235470","https://openalex.org/W6684022048","https://openalex.org/W6684973485","https://openalex.org/W6765425951"],"related_works":["https://openalex.org/W3009835149","https://openalex.org/W3103545257","https://openalex.org/W3119186746","https://openalex.org/W2034713309","https://openalex.org/W2949733005","https://openalex.org/W2972399593","https://openalex.org/W2121943493","https://openalex.org/W2025545417","https://openalex.org/W2211790881","https://openalex.org/W2993527038","https://openalex.org/W1533079807","https://openalex.org/W2353464903","https://openalex.org/W2103541323","https://openalex.org/W1650504995","https://openalex.org/W2759520088","https://openalex.org/W1597048089","https://openalex.org/W1558845053","https://openalex.org/W3154040352","https://openalex.org/W37272079","https://openalex.org/W2286921057"],"abstract_inverted_index":{"In":[0],"this":[1],"letter":[2],"we":[3],"consider":[4],"infinite":[5],"horizon":[6],"discounted":[7],"dynamic":[8],"programming":[9],"problems":[10,114],"with":[11,31,98,123],"finite":[12],"state":[13,19,133],"and":[14,17,36,88,119],"control":[15],"spaces,":[16],"partial":[18,129],"observations.":[20],"We":[21,102],"discuss":[22],"an":[23,51,83],"algorithm":[24,43],"that":[25,74],"uses":[26],"multistep":[27],"lookahead,":[28],"truncated":[29],"rollout":[30],"a":[32,37,63,92,109,116,121],"known":[33],"base":[34],"policy,":[35],"terminal":[38],"cost":[39],"function":[40],"approximation.":[41],"This":[42],"is":[44,73,76,96],"also":[45],"used":[46],"for":[47,79],"policy":[48,53],"improvement":[49],"in":[50,106],"approximate":[52],"iteration":[54],"scheme,":[55],"where":[56,115],"successive":[57],"policies":[58],"are":[59],"approximated":[60],"by":[61],"using":[62],"neural":[64,100],"network":[65],"classifier.":[66],"A":[67],"novel":[68],"feature":[69],"of":[70,91,111,134],"our":[71,104],"approach":[72],"it":[75],"well":[77],"suited":[78],"distributed":[80],"computation":[81],"through":[82],"extended":[84],"belief":[85],"space":[86],"formulation":[87],"the":[89,132,135],"use":[90],"partitioned":[93],"architecture,":[94],"which":[95],"trained":[97],"multiple":[99],"networks.":[101],"apply":[103],"methods":[105],"simulation":[107],"to":[108],"class":[110],"sequential":[112],"repair":[113],"robot":[117],"inspects":[118],"repairs":[120],"pipeline":[122],"potentially":[124],"several":[125],"rupture":[126],"sites":[127],"under":[128],"information":[130],"about":[131],"pipeline.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}