{"id":"https://openalex.org/W2970999977","doi":"https://doi.org/10.1109/tsmc.2019.2931946","title":"Proximal Parameter Distribution Optimization","display_name":"Proximal Parameter Distribution Optimization","publication_year":2019,"publication_date":"2019-08-30","ids":{"openalex":"https://openalex.org/W2970999977","doi":"https://doi.org/10.1109/tsmc.2019.2931946","mag":"2970999977"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2019.2931946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2019.2931946","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: 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/A5108064895","display_name":"Xuesong Wang","orcid":"https://orcid.org/0000-0002-5327-1088"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["Xuzhou Key Laboratory of Artificial Intelligence and Big Data, School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"Xuzhou Key Laboratory of Artificial Intelligence and Big Data, School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460614","display_name":"Tianyi Li","orcid":"https://orcid.org/0000-0002-9423-6369"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Li","raw_affiliation_strings":["Xuzhou Key Laboratory of Artificial Intelligence and Big Data, School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"Xuzhou Key Laboratory of Artificial Intelligence and Big Data, School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091364297","display_name":"Yuhu Cheng","orcid":"https://orcid.org/0000-0003-2022-9999"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhu Cheng","raw_affiliation_strings":["Xuzhou Key Laboratory of Artificial Intelligence and Big Data, School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"Xuzhou Key Laboratory of Artificial Intelligence and Big Data, School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108064895"],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":0.8401,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8043393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"51","issue":"6","first_page":"3771","last_page":"3780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9854000210762024,"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/randomness","display_name":"Randomness","score":0.7340877056121826},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.727345883846283},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6367634534835815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6141246557235718},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5822263956069946},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5643008351325989},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5034570097923279},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48022016882896423},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4632915258407593},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43728065490722656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4245920777320862},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31988900899887085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26945364475250244},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12038862705230713},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07833877205848694}],"concepts":[{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.7340877056121826},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.727345883846283},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6367634534835815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6141246557235718},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5822263956069946},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5643008351325989},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5034570097923279},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48022016882896423},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4632915258407593},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43728065490722656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4245920777320862},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31988900899887085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26945364475250244},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12038862705230713},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07833877205848694},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2019.2931946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2019.2931946","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6792490895","display_name":null,"funder_award_id":"61976215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7031480287","display_name":null,"funder_award_id":"61772532","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1542595278","https://openalex.org/W1709548961","https://openalex.org/W1932847118","https://openalex.org/W1977655452","https://openalex.org/W2024390895","https://openalex.org/W2056740053","https://openalex.org/W2097117768","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2126316555","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2158782408","https://openalex.org/W2164411961","https://openalex.org/W2165150801","https://openalex.org/W2173564293","https://openalex.org/W2257979135","https://openalex.org/W2280163991","https://openalex.org/W2338719424","https://openalex.org/W2342726990","https://openalex.org/W2417786368","https://openalex.org/W2522389818","https://openalex.org/W2529601334","https://openalex.org/W2561776174","https://openalex.org/W2567015638","https://openalex.org/W2568019971","https://openalex.org/W2593766708","https://openalex.org/W2612904117","https://openalex.org/W2623491082","https://openalex.org/W2724169821","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2751973545","https://openalex.org/W2792645523","https://openalex.org/W2794363191","https://openalex.org/W2919115771","https://openalex.org/W2949194345","https://openalex.org/W2949475445","https://openalex.org/W2951266961","https://openalex.org/W2951799221","https://openalex.org/W2962767126","https://openalex.org/W2963523627","https://openalex.org/W2963639957","https://openalex.org/W2963938771","https://openalex.org/W2964043796","https://openalex.org/W2964174623","https://openalex.org/W3103780890","https://openalex.org/W4214717370","https://openalex.org/W4297791094","https://openalex.org/W4297795161","https://openalex.org/W4302570325","https://openalex.org/W4321428174","https://openalex.org/W6627932998","https://openalex.org/W6632504492","https://openalex.org/W6637616945","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6695011786","https://openalex.org/W6716474083","https://openalex.org/W6730641667","https://openalex.org/W6731334075","https://openalex.org/W6734097942","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6741002519","https://openalex.org/W6750222692","https://openalex.org/W6764214684","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3034924094","https://openalex.org/W3094954546","https://openalex.org/W1488708774","https://openalex.org/W1982811510","https://openalex.org/W4391100477","https://openalex.org/W2402189625","https://openalex.org/W4327779705","https://openalex.org/W4310560702","https://openalex.org/W1513698804","https://openalex.org/W2029712093"],"abstract_inverted_index":{"Encouraging":[0],"the":[1,11,42,48,63,67,72,80,96,101,121,126,143,150,158,165,171,174,182,185,191,203],"agent":[2,76,106],"to":[3,20,116],"explore":[4],"has":[5],"become":[6],"a":[7,87,112,117],"hot":[8],"topic":[9],"in":[10,22],"field":[12],"of":[13,44,75,82,104,134,160,173,184,209],"reinforcement":[14],"learning":[15,68,207],"(RL).":[16],"The":[17,136],"popular":[18],"approaches":[19],"engage":[21],"exploration":[23,73,102,204],"are":[24],"mainly":[25],"by":[26,35,107,130,141,169],"injecting":[27,45],"noise":[28,46],"into":[29],"neural":[30],"network":[31],"(NN)":[32],"parameters":[33],"or":[34],"augmenting":[36],"additional":[37],"intrinsic":[38,51],"motivation":[39],"term.":[40],"However,":[41],"randomness":[43],"and":[47,77,148,162,195,206,215],"metric":[49],"for":[50],"reward":[52],"must":[53],"be":[54],"chosen":[55],"manually":[56],"may":[57],"make":[58],"RL":[59,105,211],"agents":[60],"deviate":[61],"from":[62,111],"optimal":[64],"policy":[65],"during":[66],"process.":[69],"To":[70],"enhance":[71,181],"ability":[74,103,205],"simultaneously":[78],"ensure":[79],"stability":[81,183],"parameter":[83,90,110,127,137,144,151,177,186],"learning,":[84],"we":[85],"proposed":[86],"novel":[88],"proximal":[89],"distribution":[91,128,152,187],"optimization":[92,129,138],"(PPDO)":[93],"algorithm.":[94],"On":[95,120],"one":[97],"hand,":[98,123],"PPDO":[99,124,156,200],"enhances":[100],"transforming":[108],"NN":[109],"certain":[113],"single":[114],"value":[115,166],"function":[118,167],"distribution.":[119],"other":[122],"accelerates":[125],"setting":[131],"two":[132,175],"groups":[133],"parameters.":[135],"is":[139],"guided":[140],"evaluating":[142],"quality":[145],"change":[146],"before":[147],"after":[149],"update.":[153],"In":[154],"addition,":[155],"reduces":[157],"influence":[159],"bias":[161],"variance":[163],"on":[164,190],"approximation":[168],"limiting":[170],"amplitude":[172],"consecutive":[176],"updates,":[178],"which":[179],"can":[180,201],"optimization.":[188],"Experiments":[189],"OpenAI":[192],"Gym,":[193],"Atari,":[194],"MuJoCo":[196],"platforms":[197],"indicate":[198],"that":[199],"improve":[202],"efficiency":[208],"deep":[210],"algorithms,":[212],"including":[213],"DQN":[214],"A3C.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}