{"id":"https://openalex.org/W4295308578","doi":"https://doi.org/10.1109/tnnls.2022.3202192","title":"Dual Parallel Policy Iteration With Coupled Policy Improvement","display_name":"Dual Parallel Policy Iteration With Coupled Policy Improvement","publication_year":2022,"publication_date":"2022-09-12","ids":{"openalex":"https://openalex.org/W4295308578","doi":"https://doi.org/10.1109/tnnls.2022.3202192","pmid":"https://pubmed.ncbi.nlm.nih.gov/36094996"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3202192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3202192","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/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":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2022-9999","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the 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/A5085372626","display_name":"Longyang Huang","orcid":"https://orcid.org/0000-0001-5123-5043"},"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":"Longyang Huang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-5043","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the 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/A5100643265","display_name":"C. L. Philip Chen","orcid":"https://orcid.org/0000-0001-5451-7230"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"C. L. Philip Chen","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5451-7230","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","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":false,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5327-1088","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the 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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5809,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71772498,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"35","issue":"3","first_page":"4286","last_page":"4298"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9908999800682068,"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"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/dual","display_name":"Dual (grammatical number)","score":0.7312729954719543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5066583752632141},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4303250312805176}],"concepts":[{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7312729954719543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5066583752632141},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4303250312805176},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3202192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3202192","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:36094996","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36094996","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4756161396","display_name":null,"funder_award_id":"62176259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2124477018","https://openalex.org/W2145339207","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2786010338","https://openalex.org/W2798520605","https://openalex.org/W2902286283","https://openalex.org/W2904246096","https://openalex.org/W2945496654","https://openalex.org/W2945909835","https://openalex.org/W2966349401","https://openalex.org/W2990211277","https://openalex.org/W2998481030","https://openalex.org/W2998538471","https://openalex.org/W3000642679","https://openalex.org/W3044038295","https://openalex.org/W3104139512","https://openalex.org/W3106530718","https://openalex.org/W3115959388","https://openalex.org/W3125631598","https://openalex.org/W3130610232","https://openalex.org/W3135203571","https://openalex.org/W3159667783","https://openalex.org/W3169375224","https://openalex.org/W3172934943","https://openalex.org/W3178520484","https://openalex.org/W3187550742","https://openalex.org/W3196740181","https://openalex.org/W4214717370","https://openalex.org/W4300906944","https://openalex.org/W6634413486","https://openalex.org/W6678367057","https://openalex.org/W6684921986","https://openalex.org/W6734517396","https://openalex.org/W6738855998","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6751620934","https://openalex.org/W6756397360","https://openalex.org/W6772465816","https://openalex.org/W6785732539","https://openalex.org/W6791111523"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0,17],"this":[1],"article,":[2],"a":[3,76,178],"novel":[4],"coupled":[5,31,109],"policy":[6,13,27,32,66,73,88,91,110,134,157,174],"improvement":[7,33,74,111,135],"mechanism":[8,34],"is":[9,57,67,96,115,147],"developed":[10,24],"for":[11],"improving":[12],"iteration":[14,28],"(PI)":[15],"algorithms.":[16,208],"contrast":[18],"to":[19,69,92,149,160],"the":[20,23,44,47,54,60,64,71,81,86,90,99,107,122,126,142,151,156,168,193,201,205],"common":[21],"PI,":[22],"dual":[25],"parallel":[26,38,49,72,133,183],"(DPPI)":[29],"with":[30,167],"consists":[35],"of":[36,46,101,125,140],"two":[37,48,127],"PIs.":[39],"At":[40],"each":[41,132],"PI":[42,152],"step,":[43],"performances":[45],"policies":[50,129],"are":[51,136],"evaluated":[52],"and":[53,89,154,195],"better":[55],"one":[56],"defined":[58],"as":[59],"dominant":[61,65,87,144],"policy.":[62],"Then,":[63],"used":[68],"guide":[70],"in":[75,131,192],"soft":[77],"manner":[78],"by":[79,164],"constraining":[80],"Kullback-Liebler":[82],"(KL)":[83],"divergence":[84],"between":[85],"be":[93,104],"updated.":[94],"It":[95],"proven":[97],"that":[98,118,200],"convergence":[100],"DPPI":[102,166],"can":[103],"guaranteed":[105],"under":[106,119],"designed":[108],"mechanism.":[112],"Moreover,":[113],"it":[114],"clearly":[116],"shown":[117],"certain":[120],"conditions,":[121],"Q":[123],"-functions":[124],"new":[128],"obtained":[130],"larger":[137],"than":[138],"those":[139],"all":[141],"previous":[143],"policies,":[145],"which":[146],"conductive":[148],"accelerate":[150],"process":[153],"improve":[155],"learning":[158,180],"efficiency":[159],"some":[161],"extent.":[162],"Furthermore,":[163],"combining":[165],"twin":[169],"delay":[170],"deep":[171],"deterministic":[172],"(TD3)":[173],"gradient,":[175],"we":[176],"propose":[177],"reinforcement":[179],"(RL)":[181],"algorithm:":[182],"TD3":[184],"(PTD3).":[185],"Experimental":[186],"results":[187],"on":[188],"continuous-action":[189],"control":[190],"tasks":[191],"MuJoCo":[194],"OpenAI":[196],"Gym":[197],"platforms":[198],"show":[199],"proposed":[202],"PTD3":[203],"outperforms":[204],"state-of-the-art":[206],"RL":[207]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}