{"id":"https://openalex.org/W2163823238","doi":"https://doi.org/10.1109/cdc.2005.1583136","title":"Recursive Learning Automata for Control of Partially Observable Markov Decision Processes","display_name":"Recursive Learning Automata for Control of Partially Observable Markov Decision Processes","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2163823238","doi":"https://doi.org/10.1109/cdc.2005.1583136","mag":"2163823238"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2005.1583136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2005.1583136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th IEEE Conference on Decision and Control","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041693183","display_name":"Hyeong Soo Chang","orcid":"https://orcid.org/0000-0003-3298-0018"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeong Soo Chang","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, Seoul, Korea; Program of Integrated Biotechnology at Sogang University. hschang@sogang.ac.kr","Department of Computer Science and Engineering, Sogang University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, Korea; Program of Integrated Biotechnology at Sogang University. hschang@sogang.ac.kr","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048784321","display_name":"Min Fu","orcid":"https://orcid.org/0000-0001-6491-5750"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.C. Fu","raw_affiliation_strings":["The Robert H. Smith School of Business, University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Robert H. Smith School of Business, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013807415","display_name":"Steven I. Marcus","orcid":"https://orcid.org/0000-0002-4926-9567"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S.I. Marcus","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6091","last_page":"6096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9912999868392944,"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/T10142","display_name":"Formal Methods in Verification","score":0.9751999974250793,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/markov-decision-process","display_name":"Markov decision process","score":0.7953659296035767},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5760806798934937},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5656973123550415},{"id":"https://openalex.org/keywords/learning-automata","display_name":"Learning automata","score":0.5539296865463257},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5283278226852417},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5265942811965942},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.512458860874176},{"id":"https://openalex.org/keywords/finite-state-machine","display_name":"Finite-state machine","score":0.48503750562667847},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.4811064600944519},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4787275493144989},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4715309739112854},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4567415118217468},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.43862080574035645},{"id":"https://openalex.org/keywords/decision-problem","display_name":"Decision problem","score":0.4139768183231354},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.41305652260780334},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34350237250328064},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32682889699935913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2932940125465393},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2005319893360138}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7953659296035767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5760806798934937},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5656973123550415},{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.5539296865463257},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5283278226852417},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5265942811965942},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.512458860874176},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.48503750562667847},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.4811064600944519},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4787275493144989},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4715309739112854},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4567415118217468},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.43862080574035645},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.4139768183231354},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41305652260780334},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34350237250328064},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32682889699935913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2932940125465393},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2005319893360138},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2005.1583136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2005.1583136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th IEEE Conference on Decision and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1524146404","https://openalex.org/W1532688806","https://openalex.org/W1599444075","https://openalex.org/W1967037758","https://openalex.org/W2016647253","https://openalex.org/W2034725503","https://openalex.org/W2096132608","https://openalex.org/W2101130101","https://openalex.org/W2101421095","https://openalex.org/W2104830490","https://openalex.org/W2119567691","https://openalex.org/W2138914910","https://openalex.org/W2146376321","https://openalex.org/W2149476049","https://openalex.org/W2152545378","https://openalex.org/W2157790978","https://openalex.org/W2169294731","https://openalex.org/W2334782222","https://openalex.org/W6631864160","https://openalex.org/W6674155736"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1760611253","https://openalex.org/W52153049","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":{"This":[0],"paper":[1],"presents":[2],"a":[3,32,68,74,83,101],"sampling":[4],"algorithm,":[5,59],"called":[6],"\"Recursive":[7],"Automata":[8],"Sampling":[9],"Algorithm":[10],"(RASA),\"":[11],"for":[12,46,125],"control":[13],"of":[14,25,56,65,98,115],"finite":[15],"horizon":[16],"information-state":[17],"Markov":[18],"decision":[19],"processes":[20],"(MDPs),":[21],"the":[22,35,53,57,62,71,79,86,89,92,96,112],"equivalent":[23],"model":[24],"partially":[26],"observable":[27],"MDPs.":[28],"RASA":[29,110,124],"extends":[30],"in":[31,111],"recursive":[33],"manner":[34],"Pursuit":[36,58],"algorithm":[37],"designed":[38],"with":[39],"learning":[40],"automata":[41],"by":[42],"Rajaraman":[43],"and":[44,82,95,117],"Sastry":[45],"solving":[47],"stochastic":[48],"optimization":[49],"problems.":[50],"Based":[51],"on":[52,70,85],"finite-time":[54,63],"analysis":[55],"we":[60],"analyze":[61],"behavior":[64],"RASA,":[66],"providing":[67],"bound":[69,84],"probability":[72,87],"that":[73,88],"given":[75,102],"initial":[76],"state":[77],"takes":[78],"optimal":[80,93],"action,":[81],"difference":[90],"between":[91],"value":[94],"estimate":[97],"it":[99],"exceeds":[100],"error.":[103],"We":[104],"also":[105],"discuss":[106],"how":[107,118],"to":[108,119],"apply":[109],"direct":[113],"context":[114],"POMDPs":[116],"incorporate":[120],"heuristic":[121],"knowledge":[122],"into":[123],"on-line":[126],"control.":[127]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}