{"id":"https://openalex.org/W2966473263","doi":"https://doi.org/10.24963/ijcai.2019/432","title":"Monte Carlo Tree Search for Policy Optimization","display_name":"Monte Carlo Tree Search for Policy Optimization","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2966473263","doi":"https://doi.org/10.24963/ijcai.2019/432","mag":"2966473263"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/432","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/432","pdf_url":"https://www.ijcai.org/proceedings/2019/0432.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0432.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039920748","display_name":"Xiaobai Ma","orcid":"https://orcid.org/0000-0001-7491-3935"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaobai Ma","raw_affiliation_strings":["Aeronautics and Astronautics Department, Stanford University"],"affiliations":[{"raw_affiliation_string":"Aeronautics and Astronautics Department, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059066811","display_name":"Katherine Driggs-Campbell","orcid":"https://orcid.org/0000-0003-3760-9859"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Driggs-Campbell","raw_affiliation_strings":["Electrical and Computer Engineering Department, University of Illinois Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035138959","display_name":"Zongzhang Zhang","orcid":"https://orcid.org/0000-0002-9238-4747"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongzhang Zhang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068326377","display_name":"Mykel J. Kochenderfer","orcid":"https://orcid.org/0000-0002-7238-9663"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mykel J. Kochenderfer","raw_affiliation_strings":["Aeronautics and Astronautics Department, Stanford University"],"affiliations":[{"raw_affiliation_string":"Aeronautics and Astronautics Department, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039920748"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.289,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66493747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3116","last_page":"3122"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9944000244140625,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7970102429389954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6658287048339844},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6383264064788818},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.6155370473861694},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6008115410804749},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5991523861885071},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.595908522605896},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5292657613754272},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.46664005517959595},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.42221730947494507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3826275169849396},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3011414408683777},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20209941267967224}],"concepts":[{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.7970102429389954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658287048339844},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6383264064788818},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.6155370473861694},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6008115410804749},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5991523861885071},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.595908522605896},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5292657613754272},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.46664005517959595},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.42221730947494507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3826275169849396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3011414408683777},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20209941267967224},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/432","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/432","pdf_url":"https://www.ijcai.org/proceedings/2019/0432.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/432","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/432","pdf_url":"https://www.ijcai.org/proceedings/2019/0432.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.6700000166893005}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3091702697","display_name":null,"funder_award_id":"61876119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3319537635","display_name":null,"funder_award_id":"2018143","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2966473263.pdf","grobid_xml":"https://content.openalex.org/works/W2966473263.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W107054272","https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1573483709","https://openalex.org/W1600437712","https://openalex.org/W1619459736","https://openalex.org/W1625390266","https://openalex.org/W1771410628","https://openalex.org/W2000582523","https://openalex.org/W2075848246","https://openalex.org/W2107297861","https://openalex.org/W2127653865","https://openalex.org/W2130935555","https://openalex.org/W2145339207","https://openalex.org/W2342662072","https://openalex.org/W2545546008","https://openalex.org/W2591283724","https://openalex.org/W2596367596","https://openalex.org/W2736601468","https://openalex.org/W2749928749","https://openalex.org/W2761873684","https://openalex.org/W2778749116","https://openalex.org/W2779918130","https://openalex.org/W2896873963","https://openalex.org/W2951799422","https://openalex.org/W2962975462","https://openalex.org/W2964025389","https://openalex.org/W4238447998","https://openalex.org/W4394666657","https://openalex.org/W6676054783","https://openalex.org/W6755301453","https://openalex.org/W6755903938","https://openalex.org/W6863318804","https://openalex.org/W6863631769"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W2355833770","https://openalex.org/W1985458517","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2962839548","https://openalex.org/W3136325136","https://openalex.org/W3138923328"],"abstract_inverted_index":{"Gradient-based":[0],"methods":[1,23],"are":[2,39],"often":[3],"used":[4],"for":[5,51,68],"policy":[6,52,69],"optimization":[7,53,70],"in":[8,42],"deep":[9,105],"reinforcement":[10,91],"learning,":[11],"despite":[12],"being":[13],"vulnerable":[14],"to":[15,101],"local":[16,37],"optima":[17,38],"and":[18,36,59,104],"saddle":[19],"points.":[20],"Although":[21],"gradient-free":[22,60],"(e.g.,":[24],"genetic":[25,106],"algorithms":[26],"or":[27,96],"evolution":[28],"strategies)":[29],"help":[30],"mitigate":[31],"these":[32],"issues,":[33],"poor":[34],"initialization":[35],"still":[40],"concerns":[41],"highly":[43],"nonconvex":[44],"spaces.":[45],"This":[46],"paper":[47],"presents":[48],"a":[49,73],"method":[50],"based":[54],"on":[55,90],"Monte-Carlo":[56,65],"tree":[57,66],"search":[58,67],"optimization.":[61],"Our":[62],"method,":[63],"called":[64],"(MCTSPO),":[71],"provides":[72],"better":[74],"exploration-exploitation":[75],"trade-off":[76],"through":[77],"the":[78,81],"use":[79],"of":[80],"upper":[82],"confidence":[83],"bound":[84],"heuristic.":[85],"We":[86],"demonstrate":[87],"improved":[88],"performance":[89],"learning":[92],"tasks":[93],"with":[94],"deceptive":[95],"sparse":[97],"reward":[98],"functions":[99],"compared":[100],"popular":[102],"gradient-based":[103],"algorithm":[107],"baselines.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}