{"id":"https://openalex.org/W4315606066","doi":"https://doi.org/10.1109/tase.2023.3234961","title":"Continuous Control With Swarm Intelligence Based Value Function Approximation","display_name":"Continuous Control With Swarm Intelligence Based Value Function Approximation","publication_year":2023,"publication_date":"2023-01-11","ids":{"openalex":"https://openalex.org/W4315606066","doi":"https://doi.org/10.1109/tase.2023.3234961"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2023.3234961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2023.3234961","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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/A5101886919","display_name":"Wang Bi","orcid":"https://orcid.org/0000-0002-4365-0148"},"institutions":[{"id":"https://openalex.org/I4510145","display_name":"Jiangxi University of Science and Technology","ror":"https://ror.org/03q0t9252","country_code":"CN","type":"education","lineage":["https://openalex.org/I4510145"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bi Wang","raw_affiliation_strings":["Faculty of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China","institution_ids":["https://openalex.org/I4510145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100659161","display_name":"Xuelian Li","orcid":"https://orcid.org/0000-0002-0553-8569"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelian Li","raw_affiliation_strings":["School of Foreign Studies, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Foreign Studies, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715525","display_name":"Yang Chen","orcid":"https://orcid.org/0000-0001-5239-9816"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Chen","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060119548","display_name":"Jianqing Wu","orcid":"https://orcid.org/0000-0001-7198-4199"},"institutions":[{"id":"https://openalex.org/I4510145","display_name":"Jiangxi University of Science and Technology","ror":"https://ror.org/03q0t9252","country_code":"CN","type":"education","lineage":["https://openalex.org/I4510145"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqing Wu","raw_affiliation_strings":["Faculty of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China","institution_ids":["https://openalex.org/I4510145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090747655","display_name":"Bowen Zeng","orcid":"https://orcid.org/0000-0001-6183-4162"},"institutions":[{"id":"https://openalex.org/I4510145","display_name":"Jiangxi University of Science and Technology","ror":"https://ror.org/03q0t9252","country_code":"CN","type":"education","lineage":["https://openalex.org/I4510145"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Zeng","raw_affiliation_strings":["Faculty of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China","institution_ids":["https://openalex.org/I4510145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103151025","display_name":"Junfu Chen","orcid":"https://orcid.org/0000-0002-6106-6121"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfu Chen","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101886919"],"corresponding_institution_ids":["https://openalex.org/I4510145"],"apc_list":null,"apc_paid":null,"fwci":0.5315,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6955837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"21","issue":"1","first_page":"976","last_page":"988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.979200005531311,"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":0.979200005531311,"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/mathematical-optimization","display_name":"Mathematical optimization","score":0.6195735335350037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5764972567558289},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5498634576797485},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5447049140930176},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4482743740081787},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.44021496176719666},{"id":"https://openalex.org/keywords/swarm-intelligence","display_name":"Swarm intelligence","score":0.4389794170856476},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.4362486004829407},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4235795736312866},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.33719587326049805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3311765789985657},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2889633774757385},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25163352489471436}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6195735335350037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5764972567558289},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5498634576797485},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5447049140930176},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4482743740081787},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.44021496176719666},{"id":"https://openalex.org/C119487961","wikidata":"https://www.wikidata.org/wiki/Q863960","display_name":"Swarm intelligence","level":3,"score":0.4389794170856476},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.4362486004829407},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4235795736312866},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.33719587326049805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3311765789985657},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2889633774757385},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25163352489471436},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2023.3234961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2023.3234961","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G701123200","display_name":null,"funder_award_id":"2022205200100595","funder_id":"https://openalex.org/F4320324981","funder_display_name":"Jiangxi University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320324981","display_name":"Jiangxi University of Science and Technology","ror":"https://ror.org/03q0t9252"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":101,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1600437712","https://openalex.org/W1896558367","https://openalex.org/W1971942712","https://openalex.org/W2043218896","https://openalex.org/W2073696563","https://openalex.org/W2097451572","https://openalex.org/W2101539915","https://openalex.org/W2105739999","https://openalex.org/W2111935653","https://openalex.org/W2114317160","https://openalex.org/W2120968583","https://openalex.org/W2129670787","https://openalex.org/W2145225561","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2257979135","https://openalex.org/W2396820603","https://openalex.org/W2401450523","https://openalex.org/W2525954470","https://openalex.org/W2596367596","https://openalex.org/W2615790994","https://openalex.org/W2623293810","https://openalex.org/W2736601468","https://openalex.org/W2747402019","https://openalex.org/W2769883686","https://openalex.org/W2794711922","https://openalex.org/W2826386260","https://openalex.org/W2894298649","https://openalex.org/W2899702797","https://openalex.org/W2901259238","https://openalex.org/W2902876493","https://openalex.org/W2935588605","https://openalex.org/W2937399482","https://openalex.org/W2962948705","https://openalex.org/W2963470657","https://openalex.org/W2963864421","https://openalex.org/W2981410174","https://openalex.org/W2989847975","https://openalex.org/W2995890762","https://openalex.org/W2997902164","https://openalex.org/W2999596312","https://openalex.org/W3007384386","https://openalex.org/W3085531353","https://openalex.org/W3091182627","https://openalex.org/W3096740192","https://openalex.org/W3096936293","https://openalex.org/W3118210634","https://openalex.org/W3120441334","https://openalex.org/W3123099104","https://openalex.org/W3128350768","https://openalex.org/W3154264273","https://openalex.org/W3178083033","https://openalex.org/W3184387694","https://openalex.org/W3187828410","https://openalex.org/W3191504080","https://openalex.org/W3192708540","https://openalex.org/W3209616537","https://openalex.org/W4210395113","https://openalex.org/W4210616397","https://openalex.org/W4210939259","https://openalex.org/W6635902665","https://openalex.org/W6682262322","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6696324988","https://openalex.org/W6704571135","https://openalex.org/W6727685206","https://openalex.org/W6730641667","https://openalex.org/W6734206676","https://openalex.org/W6735641298","https://openalex.org/W6738596827","https://openalex.org/W6741002519","https://openalex.org/W6741471465","https://openalex.org/W6742945991","https://openalex.org/W6747473740","https://openalex.org/W6753264383","https://openalex.org/W6754113743","https://openalex.org/W6754584241","https://openalex.org/W6755903938","https://openalex.org/W6756152092","https://openalex.org/W6757469721","https://openalex.org/W6760181788","https://openalex.org/W6760616466","https://openalex.org/W6761920647","https://openalex.org/W6767082044","https://openalex.org/W6769302897","https://openalex.org/W6772880495","https://openalex.org/W6777097758","https://openalex.org/W6781960742","https://openalex.org/W6784829994","https://openalex.org/W6786120962","https://openalex.org/W6787240212","https://openalex.org/W6791798161","https://openalex.org/W6794153505","https://openalex.org/W6794802532","https://openalex.org/W6795990215","https://openalex.org/W6796807331","https://openalex.org/W6797024940","https://openalex.org/W6797943115"],"related_works":["https://openalex.org/W4239477580","https://openalex.org/W2342906992","https://openalex.org/W2950892788","https://openalex.org/W2382010653","https://openalex.org/W4288423824","https://openalex.org/W4310834702","https://openalex.org/W3177438917","https://openalex.org/W2187728727","https://openalex.org/W3002669349","https://openalex.org/W1992540298"],"abstract_inverted_index":{"Value":[0],"function":[1,57],"approximation,":[2],"such":[3],"as":[4,58,378],"Q-learning,":[5],"is":[6,26,33,228,264,368],"widely":[7],"used":[8],"in":[9,22,60,198,220,293,336,357],"the":[10,15,19,23,31,41,49,55,61,66,70,73,89,105,114,120,123,128,136,152,160,164,170,175,178,199,214,221,231,244,248,252,261,270,275,288,294,301,305,316,332,371,379,384,391],"discrete":[11,24,184],"control":[12,185,189,240,313,360,373],"rather":[13,299],"than":[14,274,300,315],"continuous":[16,222,239,312,372],"one":[17,263],"because":[18],"optimal":[20,115,154],"action":[21,32,67,116,335],"setting":[25],"more":[27,309],"easily":[28],"selected.":[29],"Optimizing":[30],"a":[34,93,208,265,326],"non-convex":[35,50],"optimization":[36,51,329],"problem":[37,52],"with":[38,100,117,143,177,211],"respect":[39,118],"to":[40,87,111,119,156,202,225,237,269,311,330,369],"complex":[42],"value":[43,56,124],"function.":[44,125],"Some":[45],"notable":[46],"studies":[47],"simplify":[48],"by":[53,64,150,217,230,343,375],"assuming":[54],"quadratic":[59],"actions":[62,155,173],"or":[63],"discretizing":[65],"space.":[68],"However,":[69],"performance":[71],"of":[72,130,139,213,234,334,365,382,395],"output":[74],"policy":[75,209],"will":[76],"decline":[77],"if":[78],"these":[79],"studies\u2019":[80],"premises":[81],"do":[82],"not":[83],"hold.":[84],"In":[85],"order":[86],"address":[88],"problem,":[90],"we":[91,133,168,323],"propose":[92],"framework":[94,206],"that":[95,212],"combines":[96],"swarm":[97,106,140,328,345],"intelligence":[98,107,141,346],"algorithms":[99,108,142,216,298,307,377],"value-based":[101,295,317,348,376],"Reinforcement":[102,235,296,349],"Learning,":[103],"where":[104,260],"are":[109,196,255,308],"employed":[110],"search":[112],"for":[113,163,174],"state":[121],"and":[122,191,246,251,347,393],"To":[126,242,319],"ensure":[127],"correctness":[129],"this":[131,321,366],"framework,":[132],"conditionally":[134],"claim":[135],"convergence":[137],"rate":[138],"high":[144],"probability.":[145],"We":[146],"then":[147],"implement":[148],"it":[149,353],"searching":[151],"batch":[153,165],"various":[157,344],"states":[158],"on":[159],"GPU":[161],"platform":[162],"training.":[166],"Furthermore,":[167],"employ":[169],"population-based":[171],"atomic":[172],"compatibility":[176],"existing":[179],"related":[180],"work":[181],"about":[182],"solving":[183],"problems.":[186],"Four":[187],"classical":[188],"models":[190],"four":[192],"robot":[193],"simulation":[194],"environments":[195],"utilized":[197],"comparisons.":[200],"According":[201],"empirical":[203],"results,":[204],"our":[205,396],"outputs":[207],"comparable":[210],"policy-based":[215,302,306],"10%":[218],"timesteps":[219],"control.":[223],"Note":[224],"Practitioners\u2014This":[226],"paper":[227],"motivated":[229],"exploration-exploitation":[232],"dilemma":[233],"Learning":[236,297,350],"solve":[238,370],"tasks.":[241],"balance":[243],"exploration":[245,250,254,290],"exploitation,":[247],"stochastic":[249,276],"prioritized":[253,262,289,385],"roughly":[256],"two":[257],"feasible":[258],"ways,":[259],"better":[266],"choice":[267],"due":[268],"higher":[271],"data":[272],"efficiency":[273,394],"one,":[277],"e.g.":[278],"<inline-formula":[279],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[280],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[281],"<tex-math":[282],"notation=\"LaTeX\">$\\varepsilon":[283],"$":[284],"</tex-math></inline-formula>":[285],"-greedy.":[286],"Normally,":[287],"works":[291],"well":[292],"ones;":[303],"meanwhile,":[304],"suitable":[310],"tasks":[314,374],"ones.":[318],"tackle":[320],"conflict,":[322],"especially":[324],"design":[325,339],"particle":[327],"maximize":[331],"Q-value":[333],"Q-learning.":[337],"Our":[338],"can":[340,354],"be":[341,355],"hybridized":[342],"algorithms.":[351],"Also,":[352],"embedded":[356],"most":[358],"intelligent":[359],"systems":[361],"easily.":[362],"The":[363,387],"aim":[364],"study":[367],"first":[380],"step":[381],"applying":[383],"exploration.":[386],"simulative":[388],"results":[389],"verify":[390],"effectiveness":[392],"design.":[397]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}