{"id":"https://openalex.org/W4403487848","doi":"https://doi.org/10.3233/faia240696","title":"Enhancing Reinforcement Learning Through Guided Search","display_name":"Enhancing Reinforcement Learning Through Guided Search","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403487848","doi":"https://doi.org/10.3233/faia240696"},"language":"en","primary_location":{"id":"doi:10.3233/faia240696","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240696","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia240696","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037997650","display_name":"J\u00e9r\u00f4me Arjonilla","orcid":"https://orcid.org/0000-0002-0082-1939"},"institutions":[{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I56435720","display_name":"Universit\u00e9 Paris Dauphine-PSL","ror":"https://ror.org/052bz7812","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580","https://openalex.org/I56435720"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"J\u00e9r\u00f4me Arjonilla","raw_affiliation_strings":["PSL University - Dauphine, Paris, France"],"raw_orcid":"https://orcid.org/0000-0002-0082-1939","affiliations":[{"raw_affiliation_string":"PSL University - Dauphine, Paris, France","institution_ids":["https://openalex.org/I56435720","https://openalex.org/I2746051580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041765212","display_name":"Abdallah Saffidine","orcid":"https://orcid.org/0000-0001-9805-8291"},"institutions":[{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I56435720","display_name":"Universit\u00e9 Paris Dauphine-PSL","ror":"https://ror.org/052bz7812","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580","https://openalex.org/I56435720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Abdallah Saffidine","raw_affiliation_strings":["PSL University - Dauphine, Paris, France"],"raw_orcid":"https://orcid.org/0000-0001-9805-8291","affiliations":[{"raw_affiliation_string":"PSL University - Dauphine, Paris, France","institution_ids":["https://openalex.org/I56435720","https://openalex.org/I2746051580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006305238","display_name":"Tristan Cazenave","orcid":"https://orcid.org/0000-0003-4669-9374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tristan Cazenave","raw_affiliation_strings":["Potassco Solutions, Potsdam, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4669-9374","affiliations":[{"raw_affiliation_string":"Potassco Solutions, Potsdam, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037997650"],"corresponding_institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I56435720"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37729596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9976000189781189,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9848999977111816,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8927094340324402},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8027325868606567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7217638492584229},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6465251445770264},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.5955525040626526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5147964358329773},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5056109428405762},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.43401920795440674},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4158337712287903},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3495544195175171},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.22571733593940735},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0626707673072815}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8927094340324402},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8027325868606567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7217638492584229},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6465251445770264},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.5955525040626526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5147964358329773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5056109428405762},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.43401920795440674},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4158337712287903},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3495544195175171},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.22571733593940735},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0626707673072815},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia240696","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240696","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-04796707v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04796707","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ECAI, IOS Press, 2024, Frontiers in Artificial Intelligence and Applications, ⟨10.3233/FAIA240696⟩","raw_type":"Proceedings"}],"best_oa_location":{"id":"doi:10.3233/faia240696","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240696","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W77704268","https://openalex.org/W1191599655","https://openalex.org/W1573483709","https://openalex.org/W1646839507","https://openalex.org/W1768032052","https://openalex.org/W1924770834","https://openalex.org/W2113228754","https://openalex.org/W2126316555","https://openalex.org/W2147800946","https://openalex.org/W2157803532","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2745868649","https://openalex.org/W2772709170","https://openalex.org/W2781726626","https://openalex.org/W2902907165","https://openalex.org/W2904246096","https://openalex.org/W2904453761","https://openalex.org/W2920362155","https://openalex.org/W2950137412","https://openalex.org/W2953981431","https://openalex.org/W2964043796","https://openalex.org/W2982705681","https://openalex.org/W2991355586","https://openalex.org/W2995298643","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3118210634","https://openalex.org/W3122690883","https://openalex.org/W3166795773","https://openalex.org/W3208460365","https://openalex.org/W4214717370","https://openalex.org/W4226257065","https://openalex.org/W4230563027","https://openalex.org/W4285796263","https://openalex.org/W4286253093","https://openalex.org/W4287018575","https://openalex.org/W4287235517","https://openalex.org/W4289294484","https://openalex.org/W4298876402","https://openalex.org/W4305033123","https://openalex.org/W4315706776","https://openalex.org/W4322729780","https://openalex.org/W4360584316","https://openalex.org/W4386811819","https://openalex.org/W4392576633","https://openalex.org/W4394652327"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"With":[0],"the":[1,147,165,180],"aim":[2],"of":[3,89,149],"improving":[4],"performance":[5,77,92,162],"in":[6,10,22,59,140,172],"Markov":[7],"Decision":[8],"Problem":[9],"an":[11],"Off-Policy":[12],"setting,":[13,62],"we":[14,158],"suggest":[15],"taking":[16],"inspiration":[17],"from":[18],"what":[19],"is":[20,31,81,105],"done":[21],"Offline":[23,28],"Reinforcement":[24],"Learning":[25],"(RL).":[26],"In":[27],"RL,":[29],"it":[30,64,80,98],"a":[32,42,60,69,85,118,152,160],"common":[33],"practice":[34],"during":[35],"policy":[36,44,50,87],"learning":[37],"to":[38,41,45,75,83,91,96,133,136,138],"maintain":[39],"proximity":[40],"reference":[43],"mitigate":[46],"uncertainty,":[47],"reduce":[48],"potential":[49],"errors,":[51],"and":[52,94,142],"help":[53],"improve":[54],"performance.":[55],"We":[56],"find":[57,84],"ourselves":[58],"different":[61],"yet":[63],"raises":[65],"questions":[66],"about":[67],"whether":[68,79],"similar":[70],"concept":[71],"can":[72],"be":[73],"applied":[74],"enhance":[76],"i.e.,":[78],"possible":[82],"guiding":[86],"capable":[88],"contributing":[90],"improvement,":[93,163],"how":[95],"incorporate":[97],"into":[99],"our":[100,130,155],"RL":[101,156],"agent.":[102],"Our":[103,174],"attention":[104],"particularly":[106],"focused":[107],"on":[108,111,179],"algorithms":[109],"based":[110],"Monte":[112],"Carlo":[113],"Tree":[114],"Search":[115],"(MCTS)":[116],"as":[117,151],"guide.":[119],"MCTS":[120,150],"renowned":[121],"for":[122,154],"its":[123,134],"state-of-the-art":[124],"capabilities":[125],"across":[126],"various":[127],"domains,":[128],"catches":[129],"interest":[131],"due":[132],"ability":[135],"converge":[137],"equilibrium":[139],"single-player":[141],"two-player":[143],"contexts.":[144],"By":[145],"harnessing":[146],"power":[148],"guide":[153],"agent,":[157],"observed":[159],"significant":[161],"surpassing":[164],"outcomes":[166],"achieved":[167],"by":[168],"utilizing":[169],"each":[170],"method":[171],"isolation.":[173],"experiments":[175],"were":[176],"carried":[177],"out":[178],"Atari":[181],"100k":[182],"benchmark.":[183]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}