{"id":"https://openalex.org/W2963763772","doi":"https://doi.org/10.1609/aaai.v33i01.33013494","title":"How to Combine Tree-Search Methods in Reinforcement Learning","display_name":"How to Combine Tree-Search Methods in Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2963763772","doi":"https://doi.org/10.1609/aaai.v33i01.33013494","mag":"2963763772"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33013494","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013494","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33013494","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090891199","display_name":"Yonathan Efroni","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yonathan Efroni","raw_affiliation_strings":["Technion \u2013 Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion \u2013 Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088301119","display_name":"Gal Dalal","orcid":"https://orcid.org/0000-0002-3166-4251"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gal Dalal","raw_affiliation_strings":["Technion, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032281855","display_name":"Bruno Scherrer","orcid":"https://orcid.org/0000-0001-6097-4489"},"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":"Bruno Scherrer","raw_affiliation_strings":["French Institute for Research in Computer Science and Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"French Institute for Research in Computer Science and Automation","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036260775","display_name":"Shie Mannor","orcid":"https://orcid.org/0000-0003-4439-7647"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shie Mannor","raw_affiliation_strings":["Technion \u2013 Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion \u2013 Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2028,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.84781537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"33","issue":"01","first_page":"3494","last_page":"3501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9914000034332275,"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":0.9914000034332275,"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/T11182","display_name":"Auction Theory and Applications","score":0.9686999917030334,"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"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9168999791145325,"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/tree","display_name":"Tree (set theory)","score":0.6867628693580627},{"id":"https://openalex.org/keywords/search-tree","display_name":"Search tree","score":0.6669532060623169},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.642707109451294},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.629640519618988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6129399538040161},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6116796731948853},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5639028549194336},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.5066397786140442},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.47064346075057983},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.45036599040031433},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.42967334389686584},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.4281390607357025},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.35967355966567993},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34332215785980225},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33234745264053345},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3108457624912262},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.29980722069740295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.279998242855072},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.1379692256450653},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.10871759057044983},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09773701429367065}],"concepts":[{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6867628693580627},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.6669532060623169},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.642707109451294},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.629640519618988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6129399538040161},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6116796731948853},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5639028549194336},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.5066397786140442},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.47064346075057983},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.45036599040031433},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.42967334389686584},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.4281390607357025},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.35967355966567993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34332215785980225},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33234745264053345},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3108457624912262},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.29980722069740295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.279998242855072},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.1379692256450653},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10871759057044983},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09773701429367065},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33013494","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013494","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4227","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4227","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4227/4105","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33013494","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013494","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1552654126","https://openalex.org/W1750311484","https://openalex.org/W1837062119","https://openalex.org/W1857660445","https://openalex.org/W1941445455","https://openalex.org/W2020609518","https://openalex.org/W2029572069","https://openalex.org/W2073107347","https://openalex.org/W2114735315","https://openalex.org/W2119567691","https://openalex.org/W2124477018","https://openalex.org/W2126316555","https://openalex.org/W2260756217","https://openalex.org/W2527551115","https://openalex.org/W2766447205","https://openalex.org/W2772709170","https://openalex.org/W2786970706","https://openalex.org/W2803533594","https://openalex.org/W2804460413","https://openalex.org/W2949072975","https://openalex.org/W2963049774","https://openalex.org/W2963165111","https://openalex.org/W2963763772","https://openalex.org/W2963977696","https://openalex.org/W2964043796","https://openalex.org/W4214717370","https://openalex.org/W6608490358","https://openalex.org/W6640314373","https://openalex.org/W6677041917","https://openalex.org/W6679121739","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W48124421","https://openalex.org/W2960956696","https://openalex.org/W2293223786","https://openalex.org/W2770627170","https://openalex.org/W4327811054","https://openalex.org/W2120739134","https://openalex.org/W4206302813","https://openalex.org/W2184426101","https://openalex.org/W2951478555","https://openalex.org/W4322703856"],"abstract_inverted_index":{"Finite-horizon":[0],"lookahead":[1,16],"policies":[2,17],"are":[3,18],"abundantly":[4],"used":[5],"in":[6,31,48,91,169],"Reinforcement":[7],"Learning":[8],"and":[9,93,104,137,181],"demonstrate":[10],"impressive":[11],"empirical":[12],"success.":[13],"Usually,":[14],"the":[15,39,55,59,62,66,75,80,86,107,110,117,120,123,134,140,166,170,177],"implemented":[19],"with":[20],"specific":[21],"planning":[22,40],"methods":[23],"such":[24],"as":[25,42],"Monte":[26],"Carlo":[27],"Tree":[28],"Search":[29],"(e.g.":[30],"AlphaZero":[32],"(Silver":[33],"et":[34],"al.":[35],"2017b)).":[36],"Referring":[37],"to":[38,52,114,127,175],"problem":[41],"tree":[43,112,141,178],"search,":[44],"a":[45,128,150],"reasonable":[46],"practice":[47],"these":[49],"implementations":[50],"is":[51,68,89,96,102,133,139],"back":[53,115],"up":[54,116],"value":[56,182],"only":[57],"at":[58,65,119],"leaves":[60],"while":[61],"information":[63],"obtained":[64],"root":[67],"not":[69,97],"leveraged":[70],"other":[71],"than":[72],"for":[73,161],"updating":[74],"policy.":[76],"Here,":[77],"we":[78,147],"question":[79],"potency":[81],"of":[82,122,165,172],"this":[83],"approach.":[84],"Namely,":[85],"latter":[87],"procedure":[88],"non-contractive":[90],"general,":[92],"its":[94],"convergence":[95,159],"guaranteed.":[98],"Our":[99],"proposed":[100],"enhancement":[101,168],"straightforward":[103],"simple:":[105],"use":[106],"return":[108],"from":[109],"optimal":[111],"path":[113],"values":[118],"descendants":[121],"root.":[124],"This":[125],"leads":[126],"\u03b3h-contracting":[129],"procedure,":[130],"where":[131],"\u03b3":[132],"discount":[135],"factor":[136],"h":[138],"depth.":[142],"To":[143],"establish":[144],"our":[145],"results,":[146],"first":[148],"introduce":[149],"notion":[151],"called":[152],"multiple-step":[153],"greedy":[154],"consistency.":[155],"We":[156],"then":[157],"provide":[158],"rates":[160],"two":[162],"algorithmic":[163],"instantiations":[164],"above":[167],"presence":[171],"noise":[173],"injected":[174],"both":[176],"search":[179],"stage":[180],"estimation":[183],"stage.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}