{"id":"https://openalex.org/W2030570208","doi":"https://doi.org/10.1109/ita.2014.6804269","title":"Reinforcement learning, particle filters and the EM algorithm","display_name":"Reinforcement learning, particle filters and the EM algorithm","publication_year":2014,"publication_date":"2014-02-01","ids":{"openalex":"https://openalex.org/W2030570208","doi":"https://doi.org/10.1109/ita.2014.6804269","mag":"2030570208"},"language":"en","primary_location":{"id":"doi:10.1109/ita.2014.6804269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ita.2014.6804269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 Information Theory and Applications Workshop (ITA)","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/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":true,"raw_author_name":"Vivek S. Borkar","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Mumbai, India","Dept. of Electr. Eng., Indian Inst. of Technol. Bombay, Mumbai, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Indian Inst. of Technol. Bombay, Mumbai, India#TAB#","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044945068","display_name":"Ankushkumar Jain","orcid":null},"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":"Ankushkumar Jain","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Mumbai, India","Dept. of Electr. Eng., Indian Inst. of Technol. Bombay, Mumbai, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Indian Inst. of Technol. Bombay, Mumbai, India#TAB#","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018541798"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.08333653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9987999796867371,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9987999796867371,"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/T10928","display_name":"Probabilistic and Robust Engineering Design","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10968","display_name":"Statistical Distribution Estimation and Applications","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.827315628528595},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.7238245010375977},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.5888023376464844},{"id":"https://openalex.org/keywords/likelihood-function","display_name":"Likelihood function","score":0.5700677037239075},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.5564857125282288},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5541634559631348},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5475795865058899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5386111736297607},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.50105881690979},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4970286190509796},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4898967146873474},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46835842728614807},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4654771685600281},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.45236936211586},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4158025085926056},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.41456738114356995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39255693554878235},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3215835988521576},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.2533990144729614},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22933506965637207},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1975555717945099},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.11514401435852051},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11016049981117249}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.827315628528595},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.7238245010375977},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.5888023376464844},{"id":"https://openalex.org/C89106044","wikidata":"https://www.wikidata.org/wiki/Q45284","display_name":"Likelihood function","level":3,"score":0.5700677037239075},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.5564857125282288},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5541634559631348},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5475795865058899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5386111736297607},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.50105881690979},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4970286190509796},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4898967146873474},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46835842728614807},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4654771685600281},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45236936211586},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4158025085926056},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.41456738114356995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39255693554878235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3215835988521576},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2533990144729614},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22933506965637207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1975555717945099},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.11514401435852051},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11016049981117249},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ita.2014.6804269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ita.2014.6804269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 Information Theory and Applications Workshop (ITA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.648.9214","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.648.9214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ita.ucsd.edu/workshop/14/files/paper/paper_1861.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323448","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W985816301","https://openalex.org/W1524028581","https://openalex.org/W1573874356","https://openalex.org/W1883186006","https://openalex.org/W2007335262","https://openalex.org/W2049633694","https://openalex.org/W2098432798","https://openalex.org/W2158126207","https://openalex.org/W2481117679","https://openalex.org/W4250389103"],"related_works":["https://openalex.org/W2898901530","https://openalex.org/W2160216316","https://openalex.org/W2577958329","https://openalex.org/W3121212717","https://openalex.org/W4247602836","https://openalex.org/W353185590","https://openalex.org/W1934728117","https://openalex.org/W4244733523","https://openalex.org/W2979432606","https://openalex.org/W1967639437"],"abstract_inverted_index":{"We":[0],"consider":[1],"a":[2,7,28],"parameter":[3],"estimation":[4],"problem":[5],"for":[6,22,34],"Hidden":[8],"Markov":[9],"Model":[10],"in":[11,25,79],"the":[12,36,51,65,72,82],"framework":[13],"of":[14,71,81],"particle":[15,26],"filters.":[16],"Using":[17],"constructs":[18],"from":[19],"reinforcement":[20],"learning":[21],"variance":[23],"reduction":[24],"filters,":[27],"simulation":[29],"based":[30],"scheme":[31,46],"is":[32],"developed":[33],"estimating":[35],"partially":[37],"observed":[38],"log-likelihood":[39],"function.":[40],"A":[41],"Kiefer-Wolfowitz":[42],"like":[43],"stochastic":[44],"approximation":[45],"maximizes":[47],"this":[48],"function":[49],"over":[50],"unknown":[52],"parameter.":[53],"The":[54],"two":[55,60],"procedures":[56],"are":[57,77],"performed":[58],"on":[59],"different":[61],"time":[62],"scales,":[63],"emulating":[64],"alternating":[66],"`expectation'":[67],"and":[68],"`maximization'":[69],"operations":[70],"EM":[73],"algorithm.":[74],"Numerical":[75],"experiments":[76],"presented":[78],"support":[80],"proposed":[83],"scheme.":[84]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}