{"id":"https://openalex.org/W1995240981","doi":"https://doi.org/10.1109/tac.2014.2314527","title":"An Argument for the Bayesian Control of Partially Observable Markov Decision Processes","display_name":"An Argument for the Bayesian Control of Partially Observable Markov Decision Processes","publication_year":2014,"publication_date":"2014-04-01","ids":{"openalex":"https://openalex.org/W1995240981","doi":"https://doi.org/10.1109/tac.2014.2314527","mag":"1995240981"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2014.2314527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2014.2314527","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Transactions on Automatic Control","raw_type":"journal-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/A5056566726","display_name":"Erik Vargo","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Erik Vargo","raw_affiliation_strings":["Department of Systems and Information Engineering, University of Virginia, Charlottesville, VA, USA","Dept. of Syst. & Inf. Eng., Univ. of Virginia, Charlottesville, VA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Systems and Information Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Dept. of Syst. & Inf. Eng., Univ. of Virginia, Charlottesville, VA, USA#TAB#","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062316763","display_name":"Randy Cogill","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Randy Cogill","raw_affiliation_strings":["Department of Systems and Information Engineering, University of Virginia, Charlottesville, VA, USA","Dept. of Syst. & Inf. Eng., Univ. of Virginia, Charlottesville, VA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Systems and Information Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Dept. of Syst. & Inf. Eng., Univ. of Virginia, Charlottesville, VA, USA#TAB#","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056566726"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":1.227,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83987344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"59","issue":"10","first_page":"2796","last_page":"2800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9951000213623047,"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":0.9951000213623047,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9843999743461609,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.805894136428833},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7346243858337402},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.5822674632072449},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5635006427764893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5411616563796997},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5163291692733765},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.509543240070343},{"id":"https://openalex.org/keywords/decision-theory","display_name":"Decision theory","score":0.5046535730361938},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4713570475578308},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46531179547309875},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43409860134124756},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4129326045513153},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38245561718940735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3273047208786011},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3204355239868164},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13192155957221985}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.805894136428833},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7346243858337402},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5822674632072449},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5635006427764893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5411616563796997},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5163291692733765},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.509543240070343},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.5046535730361938},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4713570475578308},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46531179547309875},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43409860134124756},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4129326045513153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38245561718940735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3273047208786011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3204355239868164},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13192155957221985},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2014.2314527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2014.2314527","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G778903411","display_name":null,"funder_award_id":"CMMI-1030832","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W83428004","https://openalex.org/W107262940","https://openalex.org/W180325379","https://openalex.org/W1496855202","https://openalex.org/W1497039698","https://openalex.org/W1941248864","https://openalex.org/W1965878388","https://openalex.org/W1992821128","https://openalex.org/W2032100464","https://openalex.org/W2036931518","https://openalex.org/W2057571146","https://openalex.org/W2069045459","https://openalex.org/W2116686327","https://openalex.org/W2135681007","https://openalex.org/W2144088174","https://openalex.org/W2168318917","https://openalex.org/W2168839459","https://openalex.org/W2725122918","https://openalex.org/W3004707083","https://openalex.org/W4297728898","https://openalex.org/W6629614444","https://openalex.org/W6640661648","https://openalex.org/W6677241066","https://openalex.org/W6681718981","https://openalex.org/W6684985892"],"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":{"This":[0],"technical":[1],"note":[2],"concerns":[3],"the":[4,18,27,40,46,55,71,82,93],"control":[5,28,47,73],"of":[6],"partially":[7],"observable":[8],"Markov":[9,21,95],"decision":[10,96],"processes":[11],"characterized":[12],"by":[13,33],"a":[14,36,64],"prior":[15],"distribution":[16],"over":[17],"underlying":[19],"hidden":[20],"model":[22,41],"parameters.":[23],"In":[24],"such":[25,103],"instances,":[26],"problem":[29],"is":[30,50,60,88],"commonly":[31],"simplified":[32],"first":[34],"choosing":[35],"point":[37,56],"estimate":[38],"from":[39],"prior,":[42],"and":[43],"then":[44],"selecting":[45],"policy":[48],"that":[49,69],"optimal":[51,84],"with":[52],"respect":[53],"to":[54,61,99],"estimate.":[57],"Our":[58],"contribution":[59],"demonstrate,":[62],"through":[63],"tractable":[65],"yet":[66],"nontrivial":[67],"example,":[68],"even":[70],"best":[72],"policies":[74],"constructed":[75],"in":[76,92],"this":[77,87],"manner":[78],"can":[79],"significantly":[80],"underperform":[81],"Bayes":[83],"policy.":[85],"While":[86],"an":[89],"operative":[90],"assumption":[91],"Bayes-adaptive":[94],"process":[97],"literature,":[98],"our":[100],"knowledge":[101],"no":[102],"illustrative":[104],"example":[105],"has":[106],"been":[107],"formally":[108],"proposed.":[109]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}