{"id":"https://openalex.org/W2161632769","doi":"https://doi.org/10.1109/adprl.2013.6614991","title":"Optimistic planning for continuous-action deterministic systems","display_name":"Optimistic planning for continuous-action deterministic systems","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W2161632769","doi":"https://doi.org/10.1109/adprl.2013.6614991","mag":"2161632769"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2013.6614991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6614991","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":"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/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Lucian Busoniu","raw_affiliation_strings":["Department of Automation, Technical University of Cluj-Napoca, Romania, France"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Technical University of Cluj-Napoca, Romania, France","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036958197","display_name":"Alexander Daniels","orcid":null},"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":"Alexander Daniels","raw_affiliation_strings":["DCSC, Delft University of Technology, the Netherlands"],"affiliations":[{"raw_affiliation_string":"DCSC, Delft University of Technology, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","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 informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210138412","display_name":"Centre de recherche Inria Lille - Nord Europe","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":["Team SequeL, INRIA Lille-Nord Europe, France"],"affiliations":[{"raw_affiliation_string":"Team SequeL, INRIA Lille-Nord Europe, France","institution_ids":["https://openalex.org/I4210138412","https://openalex.org/I1326498283"]}]},{"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":["DCSC, Delft University of Technology, the Netherlands"],"affiliations":[{"raw_affiliation_string":"DCSC, Delft University of Technology, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058935509"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":4.809,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95064366,"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":"69","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9965000152587891,"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/discretization","display_name":"Discretization","score":0.8567525148391724},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.664257287979126},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6538228988647461},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.6188479065895081},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6074482798576355},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.501380443572998},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.489062637090683},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.47160205245018005},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.44479039311408997},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4319092035293579},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.42914247512817383},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.388126015663147},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31312042474746704},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17446672916412354}],"concepts":[{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.8567525148391724},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.664257287979126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6538228988647461},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.6188479065895081},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6074482798576355},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.501380443572998},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.489062637090683},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47160205245018005},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.44479039311408997},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4319092035293579},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.42914247512817383},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.388126015663147},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31312042474746704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17446672916412354},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/adprl.2013.6614991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6614991","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.671.7623","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.671.7623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://researchers.lille.inria.fr/%7Emunos/papers/files/adprl13-soop.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W21891419","https://openalex.org/W654043955","https://openalex.org/W1512919909","https://openalex.org/W1515308897","https://openalex.org/W1540821927","https://openalex.org/W1578598783","https://openalex.org/W1601081659","https://openalex.org/W1625390266","https://openalex.org/W1626155273","https://openalex.org/W2073384958","https://openalex.org/W2096678000","https://openalex.org/W2097451572","https://openalex.org/W2098432798","https://openalex.org/W2103581319","https://openalex.org/W2152475379","https://openalex.org/W2165357696","https://openalex.org/W2169511307","https://openalex.org/W2183455062","https://openalex.org/W2186241545","https://openalex.org/W2268509491","https://openalex.org/W2305373430","https://openalex.org/W2399790246","https://openalex.org/W2611243847","https://openalex.org/W6621870883","https://openalex.org/W6632480443","https://openalex.org/W6636578284","https://openalex.org/W6674603744","https://openalex.org/W6684679486"],"related_works":["https://openalex.org/W1932159282","https://openalex.org/W4285537323","https://openalex.org/W2379312070","https://openalex.org/W2136173754","https://openalex.org/W2110050003","https://openalex.org/W2953025626","https://openalex.org/W2499081552","https://openalex.org/W2366053282","https://openalex.org/W1653644965","https://openalex.org/W1974665964"],"abstract_inverted_index":{"We":[0,23],"consider":[1],"the":[2,43,48,63,66,74,110,118],"class":[3],"of":[4,53,56,65,76],"online":[5],"planning":[6,27,99],"algorithms":[7],"for":[8,33],"optimal":[9],"control,":[10],"which":[11,93],"compared":[12],"to":[13,46],"dynamic":[14],"programming":[15],"are":[16],"relatively":[17],"unaffected":[18],"by":[19,89],"large":[20],"state":[21],"dimensionality.":[22],"introduce":[24],"a":[25,84,90],"novel":[26],"algorithm":[28],"called":[29],"SOOP":[30,41,68,106],"that":[31],"works":[32],"deterministic":[34],"systems":[35],"with":[36,97],"continuous":[37,57],"states":[38],"and":[39,124],"actions.":[40],"is":[42],"first":[44],"method":[45],"explore":[47],"true":[49],"solution":[50],"space,":[51],"consisting":[52],"infinite":[54],"sequences":[55],"actions,":[58],"without":[59],"requiring":[60],"knowledge":[61],"about":[62],"smoothness":[64],"system.":[67],"can":[69],"be":[70],"used":[71],"parameter-free":[72],"at":[73],"cost":[75],"more":[77,85],"model":[78],"calls,":[79],"but":[80],"we":[81],"also":[82],"propose":[83],"practical":[86],"variant":[87],"tuned":[88],"parameter":[91],"\u03b1,":[92],"balances":[94],"finer":[95],"discretization":[96],"longer":[98],"horizons.":[100],"Experiments":[101],"on":[102],"three":[103],"problems":[104],"show":[105],"reliably":[107],"ranks":[108],"among":[109],"best":[111],"algorithms,":[112],"fully":[113],"dominating":[114],"competing":[115],"methods":[116],"when":[117],"problem":[119],"requires":[120],"both":[121],"long":[122],"horizons":[123],"fine":[125],"discretization.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}