{"id":"https://openalex.org/W2159103845","doi":"https://doi.org/10.1109/adprl.2011.5967375","title":"Optimistic planning for sparsely stochastic systems","display_name":"Optimistic planning for sparsely stochastic systems","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2159103845","doi":"https://doi.org/10.1109/adprl.2011.5967375","mag":"2159103845"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2011.5967375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lucian Busoniu","raw_affiliation_strings":["Delft Center of Systems and Control, Delft University of Technnology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center of Systems and Control, Delft University of Technnology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016419651","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"]},{"id":"https://openalex.org/I4210138412","display_name":"Centre Inria de l'Universit\u00e9 de Lille","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Remi Munos","raw_affiliation_strings":["SequeL team, INRIA Lille Nord Europe, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SequeL team, INRIA Lille Nord Europe, France","institution_ids":["https://openalex.org/I4210138412","https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026547410","display_name":"Bart De Schutter","orcid":"https://orcid.org/0000-0001-9867-6196"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Bart De Schutter","raw_affiliation_strings":["Delft Center of Systems and Control, Delft University of Technnology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center of Systems and Control, Delft University of Technnology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084264842","display_name":"Robert Babu\u0161ka","orcid":"https://orcid.org/0000-0001-9578-8598"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Robert Babuska","raw_affiliation_strings":["Delft Center of Systems and Control, Delft University of Technnology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center of Systems and Control, Delft University of Technnology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0343,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96933154,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"17","issue":null,"first_page":"48","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9979000091552734,"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":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.6962189674377441},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6547024250030518},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5479084253311157},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5211891531944275},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.5060984492301941},{"id":"https://openalex.org/keywords/successor-cardinal","display_name":"Successor cardinal","score":0.4711305797100067},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4524692893028259},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.438896507024765},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43832895159721375},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.41935813426971436},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.41777223348617554},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3928462564945221},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30925387144088745},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.2807973623275757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27327221632003784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21158254146575928},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2017754316329956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6962189674377441},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6547024250030518},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5479084253311157},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5211891531944275},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.5060984492301941},{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.4711305797100067},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4524692893028259},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.438896507024765},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43832895159721375},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41935813426971436},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.41777223348617554},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3928462564945221},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30925387144088745},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2807973623275757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27327221632003784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21158254146575928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2017754316329956},{"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},{"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/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/adprl.2011.5967375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W292508636","https://openalex.org/W1424654272","https://openalex.org/W1512919909","https://openalex.org/W1515308897","https://openalex.org/W1540821927","https://openalex.org/W1561941139","https://openalex.org/W1578598783","https://openalex.org/W1625390266","https://openalex.org/W1626155273","https://openalex.org/W1969133711","https://openalex.org/W2073384958","https://openalex.org/W2098432798","https://openalex.org/W2100857832","https://openalex.org/W2103263764","https://openalex.org/W2103581319","https://openalex.org/W2105066050","https://openalex.org/W2108051346","https://openalex.org/W2108273438","https://openalex.org/W2121863487","https://openalex.org/W2135721773","https://openalex.org/W2150490089","https://openalex.org/W2165357696","https://openalex.org/W2168405694","https://openalex.org/W2169511307","https://openalex.org/W2213594914","https://openalex.org/W2268509491","https://openalex.org/W2333635821","https://openalex.org/W2489939061","https://openalex.org/W2611243847","https://openalex.org/W2737668828","https://openalex.org/W4214717370","https://openalex.org/W4299401133","https://openalex.org/W6675713325","https://openalex.org/W6675735773","https://openalex.org/W6684548752","https://openalex.org/W6684679486"],"related_works":["https://openalex.org/W2473542051","https://openalex.org/W3123320268","https://openalex.org/W2994519609","https://openalex.org/W2726593096","https://openalex.org/W2054269721","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W3087810330","https://openalex.org/W4255368532","https://openalex.org/W3121701644"],"abstract_inverted_index":{"We":[0,112],"propose":[1],"an":[2],"online":[3,135],"planning":[4,35,107],"algorithm":[5,32,70,103,117,127],"for":[6,108],"finite-action,":[7],"sparsely":[8,109],"stochastic":[9,110,143],"Markov":[10],"decision":[11],"processes,":[12],"in":[13,23,91],"which":[14],"the":[15,61,69,85,95,101,115,133],"random":[16],"state":[17,53],"transitions":[18],"can":[19,118],"only":[20],"end":[21],"up":[22],"a":[24,34,73,77,138],"small":[25],"number":[26,80],"of":[27,81,137],"possible":[28,49],"next":[29],"states.":[30,51],"The":[31,126],"builds":[33],"tree":[36],"by":[37],"iteratively":[38],"expanding":[39],"states,":[40],"where":[41],"each":[42],"expansion":[43],"exploits":[44],"sparsity":[45],"to":[46,54,59,71],"add":[47],"all":[48],"successor":[50],"Each":[52],"expand":[55],"is":[56,89,104],"actively":[57],"chosen":[58],"improve":[60],"knowledge":[62],"about":[63],"action":[64,75],"quality,":[65],"and":[66],"this":[67],"allows":[68],"return":[72],"good":[74],"after":[76],"strictly":[78],"limited":[79],"expansions.":[82],"More":[83],"specifically,":[84],"active":[86],"selection":[87],"method":[88],"optimistic":[90,106],"that":[92,114],"it":[93],"chooses":[94],"most":[96],"promising":[97,129],"states":[98],"first,":[99],"so":[100],"novel":[102],"called":[105],"systems.":[111],"note":[113],"new":[116],"also":[119],"be":[120],"seen":[121],"as":[122],"model-predictive":[123],"(receding-horizon)":[124],"control.":[125],"obtains":[128],"numerical":[130],"results,":[131],"including":[132],"successful":[134],"control":[136],"simulated":[139],"HIV":[140],"infection":[141],"with":[142],"drug":[144],"effectiveness.":[145]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}