{"id":"https://openalex.org/W4312425502","doi":"https://doi.org/10.1109/saci55618.2022.9919518","title":"Monte Carlo Tree Search to Compare Reward Functions for Reinforcement Learning","display_name":"Monte Carlo Tree Search to Compare Reward Functions for Reinforcement Learning","publication_year":2022,"publication_date":"2022-05-25","ids":{"openalex":"https://openalex.org/W4312425502","doi":"https://doi.org/10.1109/saci55618.2022.9919518"},"language":"en","primary_location":{"id":"doi:10.1109/saci55618.2022.9919518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saci55618.2022.9919518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5074225709","display_name":"B\u00e1lint K\u0151v\u00e1ri","orcid":"https://orcid.org/0000-0003-2178-2921"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Balint Kovari","raw_affiliation_strings":["Budapest Univ. of Technology and Economics,Department of Control for Transportation and Vehicle Systems,Budapest,Hungary","Department of Control for Transportation and Vehicle Systems, Budapest Univ. of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest Univ. of Technology and Economics,Department of Control for Transportation and Vehicle Systems,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Department of Control for Transportation and Vehicle Systems, Budapest Univ. of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024746666","display_name":"B\u00e1lint Pelenczei","orcid":"https://orcid.org/0000-0001-9194-8574"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Balint Pelenczei","raw_affiliation_strings":["Budapest Univ. of Technology and Economics,Department of Control for Transportation and Vehicle Systems,Budapest,Hungary","Department of Control for Transportation and Vehicle Systems, Budapest Univ. of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest Univ. of Technology and Economics,Department of Control for Transportation and Vehicle Systems,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Department of Control for Transportation and Vehicle Systems, Budapest Univ. of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000436758","display_name":"Tam\u00e1s B\u00e9csi","orcid":"https://orcid.org/0000-0002-1487-9672"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tamas Becsi","raw_affiliation_strings":["Budapest Univ. of Technology and Economics,Department of Control for Transportation and Vehicle Systems,Budapest,Hungary","Department of Control for Transportation and Vehicle Systems, Budapest Univ. of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest Univ. of Technology and Economics,Department of Control for Transportation and Vehicle Systems,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Department of Control for Transportation and Vehicle Systems, Budapest Univ. of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":0.4424,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54726416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"000123","last_page":"000128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9675999879837036,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9675999879837036,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.9449999928474426,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.902999997138977,"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/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.8879966735839844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7507510781288147},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7362202405929565},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6408536434173584},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.6313204169273376},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5462803244590759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5118629336357117},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5017144680023193},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.45465990900993347},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.44835197925567627},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44778144359588623},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.42063191533088684},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35526466369628906},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1566982865333557},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08972802758216858},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08077943325042725}],"concepts":[{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.8879966735839844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507510781288147},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7362202405929565},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6408536434173584},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.6313204169273376},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5462803244590759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5118629336357117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5017144680023193},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.45465990900993347},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.44835197925567627},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44778144359588623},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.42063191533088684},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35526466369628906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1566982865333557},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08972802758216858},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08077943325042725},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/saci55618.2022.9919518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saci55618.2022.9919518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2571592646","https://openalex.org/W4247855592","https://openalex.org/W2567165815","https://openalex.org/W2740304877","https://openalex.org/W4306904969","https://openalex.org/W4226164546","https://openalex.org/W2766259847","https://openalex.org/W2112583639","https://openalex.org/W2138720691","https://openalex.org/W3136325136"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"has":[2,38,65],"gained":[3],"tremendous":[4],"attention":[5],"recently,":[6],"thanks":[7],"to":[8,66,81,108],"its":[9],"excellent":[10],"solutions":[11],"in":[12],"several":[13],"challenging":[14],"domains.":[15],"However,":[16],"the":[17,20,32,36,41,46,52,59,73,85,92,110,120,129,133,136,140,147,155,159],"formulation":[18],"of":[19,135,158],"reward":[21,48,87,149],"signal":[22],"is":[23,31,49,106],"always":[24],"difficult":[25],"and":[26,83],"crucially":[27],"important":[28],"since":[29,51],"it":[30],"only":[33],"guidance":[34],"that":[35,72,91,125],"agent":[37],"for":[39,98,150],"solving":[40],"given":[42],"control":[43],"task.":[44,101],"Finding":[45],"proper":[47],"time-consuming":[50],"model":[53],"must":[54],"be":[55,67,79,96],"trained":[56,107],"with":[57,115],"all":[58],"potential":[60],"candidates.":[61],"Finally,":[62],"a":[63,100],"comparison":[64],"conducted.":[68],"This":[69],"paper":[70],"proposes":[71],"Monte-Carlo":[74,141],"Tree":[75,142],"Search":[76,143],"algorithm":[77,94,105,144],"can":[78,95,145],"used":[80,97],"compare":[82],"rank":[84],"different":[86,116],"strategies.":[88],"To":[89],"see":[90],"search":[93],"such":[99],"A":[102],"Policy":[103],"Gradient":[104],"solve":[109],"Traffic":[111],"Signal":[112],"Control":[113],"problem":[114],"rewarding":[117,137],"strategies":[118],"from":[119],"literature.":[121],"The":[122],"results":[123],"show":[124],"both":[126],"methods":[127],"suggest":[128],"same":[130],"order":[131],"between":[132],"performances":[134],"concepts.":[138],"Hence":[139],"find":[146],"best":[148],"training,":[151],"which":[152],"seriously":[153],"decreases":[154],"resource":[156],"intensity":[157],"entire":[160],"process.":[161]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}