{"id":"https://openalex.org/W1998630552","doi":"https://doi.org/10.1109/adprl.2014.7010615","title":"An analysis of optimistic, best-first search for minimax sequential decision making","display_name":"An analysis of optimistic, best-first search for minimax sequential decision making","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1998630552","doi":"https://doi.org/10.1109/adprl.2014.7010615","mag":"1998630552"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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","Departmentof Automation Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Departmentof Automation Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"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 informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Remi Munos","raw_affiliation_strings":["Team SequeL, INRIA Lille, France","Team SequeL INRIA Lille, France"],"affiliations":[{"raw_affiliation_string":"Team SequeL, INRIA Lille, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Team SequeL INRIA Lille, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067955831","display_name":"El\u0151d P\u00e1ll","orcid":"https://orcid.org/0000-0002-8975-1171"},"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":false,"raw_author_name":"Elod Pall","raw_affiliation_strings":["Department of Automation, Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058935509"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":2.4541,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.9044335,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9998999834060669,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9945999979972839,"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":0.991100013256073,"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/minimax","display_name":"Minimax","score":0.6444884538650513},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.600532054901123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5374768972396851},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5262491106987},{"id":"https://openalex.org/keywords/branching","display_name":"Branching (polymer chemistry)","score":0.47038164734840393},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.46083691716194153},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.41474005579948425}],"concepts":[{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.6444884538650513},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.600532054901123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5374768972396851},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5262491106987},{"id":"https://openalex.org/C206175624","wikidata":"https://www.wikidata.org/wiki/Q595731","display_name":"Branching (polymer chemistry)","level":2,"score":0.47038164734840393},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.46083691716194153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41474005579948425},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/adprl.2014.7010615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.672.907","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.672.907","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/adprl14.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1424654272","https://openalex.org/W1515308897","https://openalex.org/W1540821927","https://openalex.org/W1561941139","https://openalex.org/W1598317541","https://openalex.org/W1625390266","https://openalex.org/W1659605498","https://openalex.org/W1985614781","https://openalex.org/W2073107347","https://openalex.org/W2083514324","https://openalex.org/W2085081875","https://openalex.org/W2088182101","https://openalex.org/W2096678000","https://openalex.org/W2124622524","https://openalex.org/W2157803532","https://openalex.org/W2159103845","https://openalex.org/W2161632769","https://openalex.org/W2169511307","https://openalex.org/W2183455062","https://openalex.org/W2186241545","https://openalex.org/W2213594914","https://openalex.org/W2333635821","https://openalex.org/W2611243847","https://openalex.org/W4238286944","https://openalex.org/W6636578284","https://openalex.org/W6674603744","https://openalex.org/W6684679486"],"related_works":["https://openalex.org/W2016058626","https://openalex.org/W2474724840","https://openalex.org/W2895916002","https://openalex.org/W1814049089","https://openalex.org/W1977348009","https://openalex.org/W2369683208","https://openalex.org/W2084836983","https://openalex.org/W1530911128","https://openalex.org/W1555347637","https://openalex.org/W2362133437"],"abstract_inverted_index":{"We":[0,27,55],"consider":[1],"problems":[2],"in":[3,13],"which":[4,75],"a":[5,8,38,57,65,91,151],"maximizer":[6],"and":[7,96,107,147],"minimizer":[9],"agent":[10],"take":[11],"actions":[12,77],"turn,":[14],"such":[15,125],"as":[16,24,46,90,126],"games":[17],"or":[18],"optimal":[19],"control":[20,155],"with":[21,140],"uncertainty":[22],"modeled":[23],"an":[25,131],"opponent.":[26],"extend":[28],"the":[29,47,52,61,69,102,127,136],"ideas":[30],"of":[31,51,60,71,93],"optimistic":[32,137],"optimization":[33],"to":[34,100,150],"this":[35],"setting,":[36],"obtaining":[37],"search":[39,49,145],"algorithm":[40,62,139],"that":[41],"has":[42],"been":[43],"previously":[44],"considered":[45],"best-first":[48,138],"variant":[50],"B*":[53],"method.":[54],"provide":[56],"novel":[58],"analysis":[59],"relying":[63],"on":[64],"certain":[66],"structure":[67],"for":[68],"values":[70],"action":[72,112],"sequences,":[73],"under":[74],"earlier":[76],"are":[78,118],"more":[79],"important":[80],"than":[81],"later":[82],"ones.":[83],"An":[84],"asymptotic":[85],"branching":[86,128],"factor":[87],"is":[88,98],"defined":[89],"measure":[92],"problem":[94],"complexity,":[95],"it":[97,149],"used":[99],"characterize":[101],"relationship":[103],"between":[104],"computation":[105],"invested":[106],"near-optimality.":[108],"In":[109,130],"particular,":[110],"when":[111],"importance":[113],"decreases":[114],"exponentially,":[115],"convergence":[116],"rates":[117],"obtained.":[119],"Throughout,":[120],"examples":[121],"illustrate":[122],"analytical":[123],"concepts":[124],"factor.":[129],"empirical":[132],"study,":[133],"we":[134],"compare":[135],"two":[141],"classical":[142],"game":[143],"tree":[144],"methods,":[146],"apply":[148],"challenging":[152],"HIV":[153],"infection":[154],"problem.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}