{"id":"https://openalex.org/W4406403012","doi":"https://doi.org/10.1007/s40747-024-01757-w","title":"Adaptive temporal-difference learning via deep neural network function approximation: a non-asymptotic analysis","display_name":"Adaptive temporal-difference learning via deep neural network function approximation: a non-asymptotic analysis","publication_year":2025,"publication_date":"2025-01-15","ids":{"openalex":"https://openalex.org/W4406403012","doi":"https://doi.org/10.1007/s40747-024-01757-w"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-024-01757-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01757-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01757-w.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01757-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101616782","display_name":"Guoyong Wang","orcid":"https://orcid.org/0000-0002-7784-9294"},"institutions":[{"id":"https://openalex.org/I72565114","display_name":"Luoyang Institute of Science and Technology","ror":"https://ror.org/04nraex26","country_code":"CN","type":"education","lineage":["https://openalex.org/I72565114"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guoyong Wang","raw_affiliation_strings":["School of Information Engineering, Luoyang Institute of Science and Technology, Luoyang, 471023, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Luoyang Institute of Science and Technology, Luoyang, 471023, China","institution_ids":["https://openalex.org/I72565114"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102519607","display_name":"Tiange Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]},{"id":"https://openalex.org/I72565114","display_name":"Luoyang Institute of Science and Technology","ror":"https://ror.org/04nraex26","country_code":"CN","type":"education","lineage":["https://openalex.org/I72565114"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiange Fu","raw_affiliation_strings":["Longmen Laboratory, Luoyang, 471023, China","School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China"],"affiliations":[{"raw_affiliation_string":"Longmen Laboratory, Luoyang, 471023, China","institution_ids":["https://openalex.org/I72565114"]},{"raw_affiliation_string":"School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China","institution_ids":["https://openalex.org/I167383011"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103249667","display_name":"Ruijuan Zheng","orcid":"https://orcid.org/0000-0002-7490-6716"},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruijuan Zheng","raw_affiliation_strings":["School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China","institution_ids":["https://openalex.org/I167383011"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668751","display_name":"Xuhui Zhao","orcid":"https://orcid.org/0009-0009-5598-3706"},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuhui Zhao","raw_affiliation_strings":["School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China","institution_ids":["https://openalex.org/I167383011"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050705532","display_name":"Junlong Zhu","orcid":"https://orcid.org/0000-0002-6411-7035"},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlong Zhu","raw_affiliation_strings":["School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China","institution_ids":["https://openalex.org/I167383011"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087014857","display_name":"Mingchuan Zhang","orcid":"https://orcid.org/0000-0002-2523-1089"},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]},{"id":"https://openalex.org/I72565114","display_name":"Luoyang Institute of Science and Technology","ror":"https://ror.org/04nraex26","country_code":"CN","type":"education","lineage":["https://openalex.org/I72565114"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingchuan Zhang","raw_affiliation_strings":["Longmen Laboratory, Luoyang, 471023, China","School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China"],"affiliations":[{"raw_affiliation_string":"Longmen Laboratory, Luoyang, 471023, China","institution_ids":["https://openalex.org/I72565114"]},{"raw_affiliation_string":"School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China","institution_ids":["https://openalex.org/I167383011"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101616782"],"corresponding_institution_ids":["https://openalex.org/I72565114"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":2.671,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88582543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"11","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944999814033508,"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":0.9944999814033508,"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/T10320","display_name":"Neural Networks and Applications","score":0.9865999817848206,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9740999937057495,"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/computational-intelligence","display_name":"Computational intelligence","score":0.7122824192047119},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6913197040557861},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5862339735031128},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5330003499984741},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4984135627746582},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.464020311832428},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4353402256965637},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38569504022598267},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3711528778076172},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.15163776278495789},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14547300338745117}],"concepts":[{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.7122824192047119},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6913197040557861},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5862339735031128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5330003499984741},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4984135627746582},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.464020311832428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4353402256965637},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38569504022598267},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3711528778076172},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.15163776278495789},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14547300338745117},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-024-01757-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01757-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01757-w.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:fee16efbbe114378aa3e25415c641530","is_oa":true,"landing_page_url":"https://doaj.org/article/fee16efbbe114378aa3e25415c641530","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 11, Iss 2, Pp 1-19 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-024-01757-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01757-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01757-w.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5430684331","display_name":null,"funder_award_id":"62172142","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5718328903","display_name":null,"funder_award_id":"62176113","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406403012.pdf","grobid_xml":"https://content.openalex.org/works/W4406403012.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1994616650","https://openalex.org/W2091565802","https://openalex.org/W2098432798","https://openalex.org/W2145339207","https://openalex.org/W2165131254","https://openalex.org/W2602856279","https://openalex.org/W2914584698","https://openalex.org/W2964123095","https://openalex.org/W2996822312","https://openalex.org/W2997874851","https://openalex.org/W3041202696","https://openalex.org/W3117126067","https://openalex.org/W3132503596","https://openalex.org/W3167032823","https://openalex.org/W3173589300","https://openalex.org/W3206576350","https://openalex.org/W4214717370","https://openalex.org/W4297329999","https://openalex.org/W4319833529","https://openalex.org/W4367298527","https://openalex.org/W4376130206","https://openalex.org/W4382318727","https://openalex.org/W4383101221","https://openalex.org/W4390817037","https://openalex.org/W4391360925","https://openalex.org/W4395661396","https://openalex.org/W4399563162","https://openalex.org/W6871841648"],"related_works":["https://openalex.org/W4289355352","https://openalex.org/W2380199044","https://openalex.org/W2134042548","https://openalex.org/W2473364827","https://openalex.org/W2332399992","https://openalex.org/W1963273549","https://openalex.org/W4287197771","https://openalex.org/W2149541341","https://openalex.org/W3164513830","https://openalex.org/W1604608764"],"abstract_inverted_index":{"Although":[0],"deep":[1,67],"reinforcement":[2,124],"learning":[3,29,125],"has":[4],"achieved":[5],"notable":[6],"practical":[7],"achievements,":[8],"its":[9],"theoretical":[10],"foundations":[11],"have":[12],"been":[13],"scarcely":[14],"explored":[15],"until":[16],"recent":[17],"times.":[18],"Nonetheless,":[19],"the":[20,58,78,90,94,112,116],"rate":[21,104],"of":[22,61,87,93,105],"convergence":[23,103],"for":[24,75],"current":[25],"neural":[26,52,68],"temporal-difference":[27],"(TD)":[28],"algorithms":[30],"is":[31,85,119],"constrained,":[32],"largely":[33],"due":[34],"to":[35,39,44,89],"their":[36],"high":[37],"sensitivity":[38],"stepsize":[40],"choices.":[41],"In":[42,82],"order":[43],"mitigate":[45],"this":[46],"issue,":[47],"we":[48,71],"propose":[49],"an":[50],"adaptive":[51,62],"TD":[53],"algorithm":[54],"(AdaBNTD)":[55],"inspired":[56],"by":[57],"superior":[59],"performance":[60],"gradient":[63],"techniques":[64],"in":[65],"training":[66],"networks.":[69],"Simultaneously,":[70],"derive":[72],"non-asymptotic":[73],"bounds":[74],"AdaBNTD":[76,84,118],"within":[77],"Markovian":[79],"observation":[80],"framework.":[81],"particular,":[83],"capable":[86],"converging":[88],"global":[91],"optimum":[92],"mean":[95],"square":[96],"projection":[97],"Bellman":[98],"error":[99],"(MSPBE)":[100],"with":[101],"a":[102],"$${{\\mathcal":[106],"{O}}}(1/\\sqrt{K})$$":[107],",":[108],"where":[109],"K":[110],"denotes":[111],"iteration":[113],"count.":[114],"Besides,":[115],"effectiveness":[117],"also":[120],"verified":[121],"through":[122],"several":[123],"benchmark":[126],"domains.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}