{"id":"https://openalex.org/W4388675108","doi":"https://doi.org/10.1109/allerton58177.2023.10313415","title":"Online Parameter Estimation in Partially Observed Markov Decision Processes","display_name":"Online Parameter Estimation in Partially Observed Markov Decision Processes","publication_year":2023,"publication_date":"2023-09-26","ids":{"openalex":"https://openalex.org/W4388675108","doi":"https://doi.org/10.1109/allerton58177.2023.10313415"},"language":"en","primary_location":{"id":"doi:10.1109/allerton58177.2023.10313415","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/allerton58177.2023.10313415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093262518","display_name":"Sai Sumedh R. Hindupur","orcid":"https://orcid.org/0000-0002-8772-8488"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sai Sumedh R. Hindupur","raw_affiliation_strings":["Indian Institute of Technology Bombay,Department of Electrical Engineering,Mumbai,India","Department of Electrical Engineering, Indian Institute of Technology Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay,Department of Electrical Engineering,Mumbai,India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018541798","display_name":"Vivek S. Borkar","orcid":"https://orcid.org/0000-0003-0756-5402"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vivek S. Borkar","raw_affiliation_strings":["Indian Institute of Technology Bombay,Department of Electrical Engineering,Mumbai,India","Department of Electrical Engineering, Indian Institute of Technology Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay,Department of Electrical Engineering,Mumbai,India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5093262518"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18022808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7470364570617676},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6944648027420044},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5993298888206482},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5848626494407654},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.5700987577438354},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5488706827163696},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.542413592338562},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.5014083385467529},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4569684565067291},{"id":"https://openalex.org/keywords/decision-problem","display_name":"Decision problem","score":0.44500070810317993},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4417964816093445},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.44138023257255554},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4362739324569702},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.42460885643959045},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3682909905910492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3508889079093933},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3332900106906891},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2726553976535797},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.141372948884964}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7470364570617676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6944648027420044},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5993298888206482},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5848626494407654},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.5700987577438354},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5488706827163696},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.542413592338562},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.5014083385467529},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4569684565067291},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.44500070810317993},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4417964816093445},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.44138023257255554},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4362739324569702},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.42460885643959045},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3682909905910492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3508889079093933},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3332900106906891},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2726553976535797},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.141372948884964},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/allerton58177.2023.10313415","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/allerton58177.2023.10313415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W103671702","https://openalex.org/W594357522","https://openalex.org/W1580557482","https://openalex.org/W1583380718","https://openalex.org/W1657674574","https://openalex.org/W1686266550","https://openalex.org/W1966311836","https://openalex.org/W1968668741","https://openalex.org/W1972679863","https://openalex.org/W1994616650","https://openalex.org/W2004001705","https://openalex.org/W2032100464","https://openalex.org/W2049633694","https://openalex.org/W2086161653","https://openalex.org/W2107726111","https://openalex.org/W2125680092","https://openalex.org/W2158282517","https://openalex.org/W2160067530","https://openalex.org/W2168359464","https://openalex.org/W2567948266","https://openalex.org/W2962854145","https://openalex.org/W3014860839","https://openalex.org/W3210638057","https://openalex.org/W4221158689","https://openalex.org/W4224246432","https://openalex.org/W4239466562","https://openalex.org/W4250389103","https://openalex.org/W4285483628","https://openalex.org/W4300443332","https://openalex.org/W4376639574","https://openalex.org/W4388574051","https://openalex.org/W6635158338","https://openalex.org/W6636922475","https://openalex.org/W6651597697","https://openalex.org/W6683084483","https://openalex.org/W6683935339","https://openalex.org/W6751659697","https://openalex.org/W6776530296","https://openalex.org/W6809717773","https://openalex.org/W6810084060","https://openalex.org/W6840086954"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W3169161914","https://openalex.org/W4321379664"],"abstract_inverted_index":{"We":[0,36],"consider":[1],"the":[2,26,53],"problem":[3,55],"of":[4],"online":[5,54],"parameter":[6],"estimation":[7],"using":[8],"maximum":[9],"likelihood":[10],"for":[11,25,33,52],"Partially":[12],"Observed":[13],"Markov":[14],"Decision":[15],"Processes":[16],"(POMDPs).":[17],"Classical":[18],"approaches":[19],"based":[20,40],"upon":[21,41],"EM":[22],"algorithm":[23],"are":[24,30],"episodic":[27],"framework":[28],"and":[29,56,61],"not":[31],"suited":[32],"this":[34],"problem.":[35],"develop":[37,45],"a":[38,46],"methodology":[39],"extremum":[42],"seeking":[43],"to":[44],"multiple":[47],"time":[48],"scale":[49],"iterative":[50],"scheme":[51],"study":[57],"it":[58],"both":[59],"theoretically":[60],"with":[62],"numerical":[63],"experiments.":[64]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}