{"id":"https://openalex.org/W2966349401","doi":"https://doi.org/10.1109/tnnls.2019.2927227","title":"Approximate Policy-Based Accelerated Deep Reinforcement Learning","display_name":"Approximate Policy-Based Accelerated Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-08-06","ids":{"openalex":"https://openalex.org/W2966349401","doi":"https://doi.org/10.1109/tnnls.2019.2927227","mag":"2966349401","pmid":"https://pubmed.ncbi.nlm.nih.gov/31398131"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2019.2927227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2019.2927227","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/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":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5327-1088","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101732156","display_name":"Yang Gu","orcid":"https://orcid.org/0000-0002-6698-479X"},"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":"Yang Gu","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, China","institution_ids":[]}]},{"author_position":"middle","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":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2022-9999","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100756739","display_name":"Aiping Liu","orcid":"https://orcid.org/0000-0001-8849-5228"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiping Liu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-8849-5228","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","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/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"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","MO"],"is_corresponding":false,"raw_author_name":"C. L. Philip Chen","raw_affiliation_strings":["Faculty of Science and Technology, University of Macau, Macau, China","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":"Faculty of Science and Technology, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]},{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9533,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.94929859,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"31","issue":"6","first_page":"1820","last_page":"1830"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9976000189781189,"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/T12676","display_name":"Machine Learning and ELM","score":0.9753000140190125,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9232041239738464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7755651473999023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5899239778518677},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5330953001976013},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5186533331871033},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.499375581741333},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46837693452835083},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45733150839805603},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3964204490184784},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32169198989868164}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9232041239738464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7755651473999023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5899239778518677},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5330953001976013},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5186533331871033},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.499375581741333},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46837693452835083},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45733150839805603},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3964204490184784},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32169198989868164},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2019.2927227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2019.2927227","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:31398131","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31398131","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/G5750115239","display_name":null,"funder_award_id":"U1813203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G653700208","display_name":null,"funder_award_id":"61751202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7031480287","display_name":"\u57fa\u4e8e\u5c5e\u6027\u5b66\u4e60\u7684\u96f6\u6837\u672c\u56fe\u50cf\u5206\u7c7b\u7814\u7a76","funder_award_id":"61772532","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G936074557","display_name":null,"funder_award_id":"61572540","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":63,"referenced_works":["https://openalex.org/W1646707810","https://openalex.org/W1730555343","https://openalex.org/W2115211925","https://openalex.org/W2118686230","https://openalex.org/W2121863487","https://openalex.org/W2128812357","https://openalex.org/W2145339207","https://openalex.org/W2149166950","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2252918381","https://openalex.org/W2462102501","https://openalex.org/W2524771588","https://openalex.org/W2549225575","https://openalex.org/W2555255624","https://openalex.org/W2596758708","https://openalex.org/W2735929339","https://openalex.org/W2742454413","https://openalex.org/W2746553466","https://openalex.org/W2780799698","https://openalex.org/W2785556016","https://openalex.org/W2786928559","https://openalex.org/W2792305967","https://openalex.org/W2792645523","https://openalex.org/W2793020180","https://openalex.org/W2793035934","https://openalex.org/W2793798239","https://openalex.org/W2798306362","https://openalex.org/W2803623613","https://openalex.org/W2887344203","https://openalex.org/W2897007254","https://openalex.org/W2901378863","https://openalex.org/W2906829782","https://openalex.org/W2908643158","https://openalex.org/W2908925809","https://openalex.org/W2910509260","https://openalex.org/W2950471160","https://openalex.org/W2950872548","https://openalex.org/W2951799221","https://openalex.org/W2953364219","https://openalex.org/W2962847657","https://openalex.org/W2963477884","https://openalex.org/W2964006217","https://openalex.org/W2964043796","https://openalex.org/W3127461190","https://openalex.org/W4214717370","https://openalex.org/W6637597983","https://openalex.org/W6639949747","https://openalex.org/W6679100793","https://openalex.org/W6681795105","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6687688904","https://openalex.org/W6691481180","https://openalex.org/W6692846177","https://openalex.org/W6696324988","https://openalex.org/W6729556111","https://openalex.org/W6730065366","https://openalex.org/W6735506055","https://openalex.org/W6748554570","https://openalex.org/W6749032995","https://openalex.org/W6749423406"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2952356279"],"abstract_inverted_index":{"In":[0,53],"recent":[1],"years,":[2],"the":[3,25,37,46,60,76,79,105,116,144,147,156,173],"deep":[4,40,120,126],"reinforcement":[5,86],"learning":[6,47,61,87,102,111],"(DRL)":[7],"algorithms":[8,158],"have":[9,14,108,154],"been":[10],"developed":[11],"rapidly":[12],"and":[13,30,44,125,140,162],"achieved":[15],"excellent":[16],"performance":[17,167],"in":[18,172],"many":[19],"challenging":[20],"tasks.":[21,164],"However,":[22],"due":[23],"to":[24,57,94,114],"complexity":[26],"of":[27,34,39,49,63,78,82,146],"network":[28,35,41],"structure":[29],"a":[31,68,99,109],"large":[32],"amount":[33],"parameters,":[36],"training":[38],"is":[42,51,92],"time-consuming,":[43],"consequently,":[45],"efficiency":[48],"DRL":[50,64,106,135,151],"limited.":[52],"this":[54],"paper,":[55],"aiming":[56],"speed":[58],"up":[59],"process":[62],"agent,":[65],"we":[66,131],"propose":[67],"novel":[69,134],"approximate":[70,83],"policy-based":[71],"accelerated":[72,117,148],"(APA)":[73],"algorithm":[74,118,149],"from":[75],"viewpoint":[77],"error":[80],"analysis":[81],"policy":[84,128],"iteration":[85],"algorithms.":[88,152],"The":[89],"proposed":[90,132,157],"APA":[91],"proven":[93],"be":[95],"convergent":[96],"even":[97],"with":[98,119,150],"more":[100],"aggressive":[101],"rate,":[103],"making":[104],"agent":[107],"faster":[110],"speed.":[112],"Furthermore,":[113],"combine":[115],"Q-network":[121],"(DQN),":[122],"Double":[123],"DQN":[124],"deterministic":[127],"gradient":[129],"(DDPG),":[130],"three":[133],"algorithms:":[136],"APA-DQN,":[137],"APA-Double":[138],"DQN,":[139],"APA-DDPG,":[141],"which":[142],"demonstrates":[143,168],"adaptability":[145],"We":[153],"tested":[155],"on":[159],"both":[160],"discrete-action":[161],"continuous-action":[163],"Their":[165],"superior":[166],"their":[169],"great":[170],"potential":[171],"practical":[174],"applications.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}