{"id":"https://openalex.org/W2963935983","doi":"https://doi.org/10.1609/aaai.v33i01.33014675","title":"Policy Optimization with Model-Based Explorations","display_name":"Policy Optimization with Model-Based Explorations","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2963935983","doi":"https://doi.org/10.1609/aaai.v33i01.33014675","mag":"2963935983"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33014675","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014675","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4392/4270","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4392/4270","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087003458","display_name":"Feiyang Pan","orcid":"https://orcid.org/0000-0002-0103-1090"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feiyang Pan","raw_affiliation_strings":["Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016589992","display_name":"Qingpeng Cai","orcid":"https://orcid.org/0000-0001-6451-9299"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingpeng Cai","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076875538","display_name":"Anxiang Zeng","orcid":"https://orcid.org/0000-0003-3869-5357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An-Xiang Zeng","raw_affiliation_strings":["Alibaba"],"affiliations":[{"raw_affiliation_string":"Alibaba","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009472354","display_name":"Chun-Xiang Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chun-Xiang Pan","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070849903","display_name":"Qing Da","orcid":"https://orcid.org/0000-0003-2200-0098"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Da","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053490860","display_name":"Hualin He","orcid":"https://orcid.org/0009-0008-8404-847X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hualin He","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734672","display_name":"Qing He","orcid":"https://orcid.org/0000-0001-8833-5398"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing He","raw_affiliation_strings":["Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013558969","display_name":"Pingzhong Tang","orcid":"https://orcid.org/0000-0003-1330-1999"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingzhong Tang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5087003458"],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":1.0663,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82794068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"33","issue":"01","first_page":"4675","last_page":"4682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9833999872207642,"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":0.9833999872207642,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9713000059127808,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8263160586357117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6877710819244385},{"id":"https://openalex.org/keywords/pome","display_name":"Pome","score":0.5698952078819275},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5302438735961914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4468362629413605},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4426344037055969},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39664819836616516},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3949543833732605},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1662306785583496},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08880442380905151}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8263160586357117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6877710819244385},{"id":"https://openalex.org/C143108565","wikidata":"https://www.wikidata.org/wiki/Q41274","display_name":"Pome","level":2,"score":0.5698952078819275},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5302438735961914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4468362629413605},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4426344037055969},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39664819836616516},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3949543833732605},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1662306785583496},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08880442380905151},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C528095902","wikidata":"https://www.wikidata.org/wiki/Q2283886","display_name":"Pulp and paper industry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33014675","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014675","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4392/4270","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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33014675","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014675","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4392/4270","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":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3294370371","display_name":null,"funder_award_id":"2017YFB1002104","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G466649759","display_name":null,"funder_award_id":"2017Y","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5372500160","display_name":null,"funder_award_id":"No. 2017YFB1002104","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7429600474","display_name":null,"funder_award_id":"2017YFB1","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8340078520","display_name":null,"funder_award_id":"2017YF","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8823009050","display_name":null,"funder_award_id":"2017YFB","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963935983.pdf","grobid_xml":"https://content.openalex.org/works/W2963935983.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W195033972","https://openalex.org/W834081922","https://openalex.org/W1491843047","https://openalex.org/W1522301498","https://openalex.org/W1575592356","https://openalex.org/W1618543586","https://openalex.org/W1771410628","https://openalex.org/W1957496711","https://openalex.org/W2039522160","https://openalex.org/W2112420033","https://openalex.org/W2127107099","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2260756217","https://openalex.org/W2417786368","https://openalex.org/W2561776174","https://openalex.org/W2614839826","https://openalex.org/W2736601468","https://openalex.org/W2740489910","https://openalex.org/W2767313115","https://openalex.org/W2785389871","https://openalex.org/W2788079612","https://openalex.org/W2876830307","https://openalex.org/W2949475445","https://openalex.org/W2950471160","https://openalex.org/W2952509347","https://openalex.org/W2963095800","https://openalex.org/W2963430173","https://openalex.org/W2963440040","https://openalex.org/W2963523627","https://openalex.org/W2963630259","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W3103780890","https://openalex.org/W4214717370","https://openalex.org/W4234228486","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6675999342","https://openalex.org/W6678927950","https://openalex.org/W6696324988","https://openalex.org/W6741002519","https://openalex.org/W6741922412","https://openalex.org/W6743013956","https://openalex.org/W7075680496"],"related_works":["https://openalex.org/W2014531947","https://openalex.org/W2411410451","https://openalex.org/W2898086292","https://openalex.org/W2594638871","https://openalex.org/W2751134898","https://openalex.org/W1625681030","https://openalex.org/W2757467626","https://openalex.org/W1986604063","https://openalex.org/W2070987841","https://openalex.org/W2900115268"],"abstract_inverted_index":{"Model-free":[0],"reinforcement":[1,39,77],"learning":[2,40,71],"methods":[3,25,41],"such":[4,19],"as":[5,20,103,176],"the":[6,35,44,56,59,88,96,115,139,161,164,169,177,187,191],"Proximal":[7],"Policy":[8,127],"Optimization":[9,128],"algorithm":[10,117,188],"(PPO)":[11],"have":[12],"successfully":[13],"applied":[14],"in":[15,76],"complex":[16],"decision-making":[17],"problems":[18],"Atari":[21,208],"games.":[22,224],"However,":[23],"these":[24,172],"suffer":[26,54],"from":[27,55],"high":[28,31],"variances":[29],"and":[30,69,92,100,118,150,159,211],"sample":[32,49],"complexity.":[33],"On":[34],"other":[36],"hand,":[37],"model-based":[38,68,101,152],"that":[42,214],"learn":[43],"transition":[45,60,157],"dynamics":[46],"are":[47,198],"more":[48],"efficient,":[50],"but":[51],"they":[52],"often":[53],"bias":[57],"of":[58,66,106,163,171,222],"estimation.":[61],"How":[62],"to":[63,86,114,137,189,200],"make":[64],"use":[65],"both":[67],"model-free":[70,99,144],"is":[72],"a":[73,83,104,121,143,151,156],"central":[74],"problem":[75],"learning.In":[78],"this":[79,111],"paper,":[80],"we":[81],"present":[82],"new":[84,112,122],"technique":[85,113],"address":[87],"tradeoff":[89],"between":[90,98],"exploration":[91,107,179],"exploitation,":[93],"which":[94,154,197],"regards":[95],"difference":[97],"estimations":[102,175],"measure":[105],"value.":[108],"We":[109,202],"apply":[110],"PPO":[116,206,217],"arrive":[119],"at":[120],"policy":[123],"optimization":[124],"method,":[125],"named":[126],"with":[129,193,205],"Modelbased":[130],"Explorations":[131],"(POME).":[132],"POME":[133,167,204,215],"uses":[134],"two":[135,173],"components":[136],"predict":[138],"actions\u2019":[140],"target":[141,174,195],"values:":[142],"one":[145,153],"estimated":[146],"by":[147],"Monte-Carlo":[148],"sampling":[149],"learns":[155],"model":[158],"predicts":[160],"value":[162,180],"next":[165],"state.":[166],"adds":[168],"error":[170],"additional":[178],"for":[181],"each":[182],"state-action":[183],"pair,":[184],"i.e,":[185],"encourages":[186],"explore":[190],"states":[192],"larger":[194],"errors":[196],"hard":[199],"estimate.":[201],"compare":[203],"on":[207,218],"2600":[209],"games,":[210],"it":[212],"shows":[213],"outperforms":[216],"33":[219],"games":[220],"out":[221],"49":[223]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}