{"id":"https://openalex.org/W2183455062","doi":null,"title":"Optimistic Planning for Markov Decision Processes","display_name":"Optimistic Planning for Markov Decision Processes","publication_year":2012,"publication_date":"2012-04-21","ids":{"openalex":"https://openalex.org/W2183455062","mag":"2183455062"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-00756736v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-00756736","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"15th International Conference on Artificial Intelligence and Statistics, AISTATS-12, Apr 2012, La Palma, Canary Islands, Spain. pp.182-189","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-00756736","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296","observed_orcids":["https://orcid.org/0000-0001-8017-1296"]},"institutions":[{"id":"https://openalex.org/I4210110792","display_name":"CRAN","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Busoniu, Lucian","raw_affiliation_strings":["Centre de Recherche en Automatique de Nancy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre de Recherche en Automatique de Nancy","institution_ids":["https://openalex.org/I4210110792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006533777","display_name":"R\u00e9mi Munos","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Munos, Remi","raw_affiliation_strings":["Sequential Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sequential Learning","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6881,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.96310671,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"22","issue":null,"first_page":"182","last_page":"189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.00139999995008111,"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":0.00039999998989515007,"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":0.9860000014305115},{"id":"https://openalex.org/keywords/online-planning","display_name":"online planning","score":0.8529999852180481},{"id":"https://openalex.org/keywords/tree-search","display_name":"tree search","score":0.6650000214576721},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5559999942779541}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7770540714263916},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6593722105026245},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6393539309501648},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.6315203905105591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5727470517158508},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5646520256996155},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5576702952384949},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5234277248382568},{"id":"https://openalex.org/C2780388253","wikidata":"https://www.wikidata.org/wiki/Q5421508","display_name":"Exponent","level":2,"score":0.4934738874435425},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48880860209465027},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.48502108454704285},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.480478435754776},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.446610689163208},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42858415842056274},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4188278317451477},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41282764077186584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38064250349998474},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19021761417388916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17476415634155273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10196936130523682},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10065963864326477},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07469549775123596},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-00756736v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-00756736","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"15th International Conference on Artificial Intelligence and Statistics, AISTATS-12, Apr 2012, La Palma, Canary Islands, Spain. pp.182-189","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00756736v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-00756736","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"15th International Conference on Artificial Intelligence and Statistics, AISTATS-12, Apr 2012, La Palma, Canary Islands, Spain. pp.182-189","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W153346180","https://openalex.org/W1512919909","https://openalex.org/W1515308897","https://openalex.org/W1540821927","https://openalex.org/W1625390266","https://openalex.org/W1881419322","https://openalex.org/W1953015992","https://openalex.org/W2103581319","https://openalex.org/W2105066050","https://openalex.org/W2115519224","https://openalex.org/W2119567691","https://openalex.org/W2152475379","https://openalex.org/W2156361796","https://openalex.org/W2158858912","https://openalex.org/W2159103845","https://openalex.org/W2168110243","https://openalex.org/W2168405694","https://openalex.org/W2169511307","https://openalex.org/W2186241545","https://openalex.org/W2268509491","https://openalex.org/W2900134456","https://openalex.org/W3125826253"],"related_works":["https://openalex.org/W7095994484","https://openalex.org/W2106225708","https://openalex.org/W7097191741","https://openalex.org/W7095202620","https://openalex.org/W4299494854","https://openalex.org/W2189563888","https://openalex.org/W2470923384","https://openalex.org/W7096522401","https://openalex.org/W7099684830","https://openalex.org/W1512919909"],"abstract_inverted_index":{"The":[0],"reinforcement":[1],"learning":[2],"community":[3],"has":[4],"recently":[5],"intensified":[6],"its":[7,97],"interest":[8],"in":[9],"online":[10],"planning":[11,43,83],"methods,":[12],"due":[13],"to":[14,51],"their":[15],"relative":[16],"independence":[17],"on":[18,104,109],"the":[19,32,60,68,71,110,132,136,148],"state":[20],"space":[21,61],"size.":[22],"However,":[23],"tight":[24],"near-optimality":[25,69,133],"guarantees":[26],"are":[27,154],"not":[28,101],"yet":[29],"available":[30],"for":[31,94,141],"general":[33],"case":[34],"of":[35,59,62,70,88,112,128,145],"stochastic":[36],"Markov":[37],"decision":[38],"processes":[39],"and":[40,65,90,138,158],"closed-loop,":[41],"state-dependent":[42],"policies.":[44,118],"We":[45,119],"therefore":[46],"consider":[47],"an":[48],"algorithm":[49,149],"related":[50],"AO*":[52],"that":[53,114],"optimistically":[54],"explores":[55],"a":[56,85,125],"tree":[57,77],"representation":[58],"closed-loop":[63],"policies,":[64],"we":[66],"analyze":[67],"action":[72],"it":[73],"returns":[74],"after":[75],"n":[76],"node":[78],"expansions.":[79],"While":[80],"this":[81,121],"optimistic":[82],"requires":[84],"finite":[86],"number":[87],"actions":[89],"possible":[91],"next":[92],"states":[93],"each":[95],"transition,":[96],"asymptotic":[98],"performance":[99,139],"does":[100],"depend":[102],"directly":[103],"these":[105],"numbers,":[106],"but":[107],"only":[108],"subset":[111],"nodes":[113],"significantly":[115],"impact":[116],"near-optimal":[117,156],"characterize":[120],"set":[122],"by":[123],"introducing":[124],"novel":[126],"measure":[127],"problem":[129],"complexity,":[130],"called":[131],"exponent.":[134],"Specializing":[135],"exponent":[137],"bound":[140],"some":[142],"interesting":[143],"classes":[144],"MDPs":[146],"illustrates":[147],"works":[150],"better":[151],"when":[152],"there":[153],"fewer":[155],"policies":[157],"less":[159],"uniform":[160],"transition":[161],"probabilities.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}