{"id":"https://openalex.org/W1970837196","doi":"https://doi.org/10.1109/adprl.2013.6614992","title":"Optimistic planning for belief-augmented Markov Decision Processes","display_name":"Optimistic planning for belief-augmented Markov Decision Processes","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W1970837196","doi":"https://doi.org/10.1109/adprl.2013.6614992","mag":"1970837196"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2013.6614992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6614992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},"type":"preprint","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/A5031489638","display_name":"Rapha\u00ebl Fonteneau","orcid":"https://orcid.org/0000-0002-7850-1548"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Raphael Fonteneau","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Li\u00e8ge, BELGIUM","Dept. of Electr. Eng. & Comput. Sci., Univ. of Liege, Liege, Belgium#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Li\u00e8ge, BELGIUM","institution_ids":["https://openalex.org/I157674565"]},{"raw_affiliation_string":"Dept. of Electr. Eng. & Comput. Sci., Univ. of Liege, Liege, Belgium#TAB#","institution_ids":["https://openalex.org/I157674565"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296"},"institutions":[{"id":"https://openalex.org/I4210110792","display_name":"Centre de Recherche en Automatique de Nancy","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lucian Busoniu","raw_affiliation_strings":["Universite de Lorraine, CRAN, FRANCE","CRAN, Univ. de Lorraine, Vandoeuvre les Nancy, France"],"affiliations":[{"raw_affiliation_string":"Universite de Lorraine, CRAN, FRANCE","institution_ids":["https://openalex.org/I90183372"]},{"raw_affiliation_string":"CRAN, Univ. de Lorraine, Vandoeuvre les Nancy, France","institution_ids":["https://openalex.org/I4210110792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006533777","display_name":"R\u00e9mi Munos","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Remi Munos","raw_affiliation_strings":["SequeL Team, Inria Lille, FRANCE","SequeL Team, Inria Lille - Nord Eur., Lille, France"],"affiliations":[{"raw_affiliation_string":"SequeL Team, Inria Lille, FRANCE","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"SequeL Team, Inria Lille - Nord Eur., Lille, France","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031489638"],"corresponding_institution_ids":["https://openalex.org/I157674565"],"apc_list":null,"apc_paid":null,"fwci":6.4252,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.96168522,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9959999918937683,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.728919267654419},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.6322007775306702},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6068636775016785},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5745385885238647},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5403791069984436},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.49118754267692566},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4656468331813812},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4168965816497803},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41165611147880554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3974176049232483},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3513467311859131},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3508176803588867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29686403274536133},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27952682971954346},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10617268085479736}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.728919267654419},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.6322007775306702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6068636775016785},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5745385885238647},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5403791069984436},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.49118754267692566},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4656468331813812},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4168965816497803},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41165611147880554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3974176049232483},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3513467311859131},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3508176803588867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29686403274536133},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27952682971954346},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10617268085479736},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2013.6614992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6614992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321390","display_name":"Fonds De La Recherche Scientifique - FNRS","ror":"https://ror.org/03q83t159"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W1497039698","https://openalex.org/W1505937442","https://openalex.org/W1515308897","https://openalex.org/W1540821927","https://openalex.org/W1582436621","https://openalex.org/W1591803298","https://openalex.org/W1594783240","https://openalex.org/W1625390266","https://openalex.org/W1714211023","https://openalex.org/W1850488217","https://openalex.org/W1888434271","https://openalex.org/W1973458764","https://openalex.org/W2096678000","https://openalex.org/W2097931172","https://openalex.org/W2100677568","https://openalex.org/W2103581319","https://openalex.org/W2106008679","https://openalex.org/W2116459397","https://openalex.org/W2124352385","https://openalex.org/W2125526403","https://openalex.org/W2125710232","https://openalex.org/W2126848223","https://openalex.org/W2131490088","https://openalex.org/W2157477959","https://openalex.org/W2159103845","https://openalex.org/W2159178228","https://openalex.org/W2165612525","https://openalex.org/W2168405694","https://openalex.org/W2169511307","https://openalex.org/W2171084228","https://openalex.org/W2183455062","https://openalex.org/W2268119109","https://openalex.org/W2268509491","https://openalex.org/W2341171179","https://openalex.org/W2399790246","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W2963214119","https://openalex.org/W3020125231","https://openalex.org/W3041202696","https://openalex.org/W3099235411","https://openalex.org/W4230901439","https://openalex.org/W4285719527","https://openalex.org/W4293405734","https://openalex.org/W4294239562","https://openalex.org/W6606719070","https://openalex.org/W6634907821","https://openalex.org/W6635327058","https://openalex.org/W6635508374","https://openalex.org/W6635719377","https://openalex.org/W6639039794","https://openalex.org/W6675735773","https://openalex.org/W6678635437","https://openalex.org/W6678698164","https://openalex.org/W6683042886","https://openalex.org/W6683608605","https://openalex.org/W6684679486","https://openalex.org/W6684973485","https://openalex.org/W6685780691","https://openalex.org/W6842800053"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W4225571923"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,18,22,36,40,51,56,74,79,86,91,106],"Bayesian":[4,12,103],"Optimistic":[5,23],"Planning":[6,24],"(BOP)":[7],"algorithm,":[8],"a":[9,62],"novel":[10],"model-based":[11],"reinforcement":[13],"learning":[14],"approach.":[15],"BOP":[16,75,101],"extends":[17],"planning":[19],"approach":[20],"of":[21,39],"for":[25],"Markov":[26],"Decision":[27],"Processes":[28],"(OP-MDP)":[29],"algorithm":[30,76],"[10],":[31],"[9]":[32],"to":[33,110],"contexts":[34],"where":[35],"transition":[37,68,96],"model":[38],"MDP":[41,58],"is":[42,59],"initially":[43],"unknown":[44,57],"and":[45,73],"progressively":[46],"learned":[47],"through":[48],"interactions":[49],"within":[50],"environment.":[52],"The":[53],"knowledge":[54],"about":[55],"represented":[60],"with":[61,90],"probability":[63],"distribution":[64,94],"over":[65,95],"all":[66],"possible":[67],"models":[69],"using":[70],"Dirichlet":[71],"distributions,":[72],"plans":[77],"in":[78],"belief-augmented":[80],"state":[81,88],"space":[82],"constructed":[83],"by":[84],"concatenating":[85],"original":[87],"vector":[89],"current":[92],"posterior":[93],"models.":[97],"We":[98],"show":[99,115],"that":[100],"becomes":[102],"optimal":[104],"when":[105],"budget":[107],"parameter":[108],"increases":[109],"infinity.":[111],"Preliminary":[112],"empirical":[113],"validations":[114],"promising":[116],"performance.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}