{"id":"https://openalex.org/W4205103317","doi":"https://doi.org/10.3233/jifs-211935","title":"Proximal policy optimization with model-based methods","display_name":"Proximal policy optimization with model-based methods","publication_year":2022,"publication_date":"2022-01-11","ids":{"openalex":"https://openalex.org/W4205103317","doi":"https://doi.org/10.3233/jifs-211935"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-211935","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-211935","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-article"},"type":"article","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/A5101622670","display_name":"Shuailong Li","orcid":"https://orcid.org/0009-0009-6064-9147"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuailong Li","raw_affiliation_strings":["Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China","State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China","State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100761009","display_name":"Huiwen Zhang","orcid":"https://orcid.org/0000-0002-5655-7049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huiwen Zhang","raw_affiliation_strings":["CVTE Research, Guangzhou, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVTE Research, Guangzhou, P.R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101791132","display_name":"X. Zhang","orcid":"https://orcid.org/0000-0002-5019-5729"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China","State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023270824","display_name":"Yuquan Leng","orcid":"https://orcid.org/0000-0003-4063-4545"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuquan Leng","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities, Southern University of Science and Technology, Shenzhen, China","Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems, Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems, Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023270824"],"corresponding_institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366","https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58045315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"42","issue":"6","first_page":"5399","last_page":"5410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9937000274658203,"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":0.9843000173568726,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9029158353805542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8411253094673157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5883667469024658},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5649415254592896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5490602850914001},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5281372666358948},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48344120383262634},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1826220452785492}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9029158353805542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8411253094673157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5883667469024658},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5649415254592896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5490602850914001},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5281372666358948},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48344120383262634},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1826220452785492},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-211935","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-211935","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1980035368","https://openalex.org/W2007414406","https://openalex.org/W2041176007","https://openalex.org/W2043968544","https://openalex.org/W2084912121","https://openalex.org/W2100495367","https://openalex.org/W2112483970","https://openalex.org/W2136922672","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2257979135","https://openalex.org/W2618530766","https://openalex.org/W2747592475","https://openalex.org/W2754517384","https://openalex.org/W2802679510","https://openalex.org/W2918234796","https://openalex.org/W2963525569","https://openalex.org/W2963935983","https://openalex.org/W2983824088","https://openalex.org/W3175737563"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Model-free":[0],"reinforcement":[1,43,62,123],"learning":[2],"methods":[3,20,52],"have":[4,21],"successfully":[5],"been":[6],"applied":[7],"to":[8,90,110,129],"practical":[9],"applications":[10],"such":[11,24],"as":[12,25,177],"decision-making":[13],"problems":[14],"in":[15,160,181],"Atari":[16,158],"games.":[17,183],"However,":[18],"these":[19],"inherent":[22],"shortcomings,":[23],"a":[26,54,102,131],"high":[27],"variance":[28],"and":[29,38,60,118,135],"low":[30],"sample":[31,39],"efficiency.":[32],"To":[33],"improve":[34],"the":[35,68,75,79,84,87,91,95,112,114,119,127,137,140,149,161,175,178],"policy":[36,48,97],"performance":[37],"efficiency":[40],"of":[41,57,70,78,86,94,116,121,139],"model-free":[42,61],"learning,":[44],"we":[45,154],"propose":[46],"proximal":[47,96],"optimization":[49,98],"with":[50],"model-based":[51,59,103,122],"(PPOMM),":[53],"fusion":[55],"method":[56,106,147],"both":[58],"learning.":[63,124],"PPOMM":[64,82,171],"not":[65],"only":[66],"considers":[67],"information":[69,77,85,138],"past":[71],"experience":[72],"but":[73],"also":[74],"prediction":[76],"future":[80],"state.":[81,142],"adds":[83],"next":[88,141],"state":[89],"objective":[92],"function":[93],"(PPO)":[99],"algorithm":[100,152,180],"through":[101],"method.":[104],"This":[105],"uses":[107],"two":[108],"components":[109],"optimize":[111,130],"policy:":[113],"error":[115,120],"PPO":[117,151],"We":[125],"use":[126],"latter":[128],"latent":[132],"transition":[133],"model":[134],"predict":[136],"For":[143],"most":[144],"games,":[145],"this":[146],"outperforms":[148],"state-of-the-art":[150],"when":[153],"evaluate":[155],"across":[156],"49":[157],"games":[159],"Arcade":[162],"Learning":[163],"Environment":[164],"(ALE).":[165],"The":[166],"experimental":[167],"results":[168],"show":[169],"that":[170],"performs":[172],"better":[173],"or":[174],"same":[176],"original":[179],"33":[182]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}