{"id":"https://openalex.org/W3206576350","doi":"https://doi.org/10.1109/tpami.2021.3119645","title":"Adaptive Temporal Difference Learning With Linear Function Approximation","display_name":"Adaptive Temporal Difference Learning With Linear Function Approximation","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3206576350","doi":"https://doi.org/10.1109/tpami.2021.3119645","mag":"3206576350","pmid":"https://pubmed.ncbi.nlm.nih.gov/34648431"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3119645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3119645","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5037318331","display_name":"Tao Sun","orcid":"https://orcid.org/0000-0001-5024-1900"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Sun","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-5024-1900","affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001223413","display_name":"Han Shen","orcid":"https://orcid.org/0000-0001-8537-9862"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Shen","raw_affiliation_strings":["Department of ECSE, Rensselaer Polytechnic Institute, Troy, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of ECSE, Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100783476","display_name":"Tianyi Chen","orcid":"https://orcid.org/0000-0003-3477-1439"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Chen","raw_affiliation_strings":["Department of ECSE, Rensselaer Polytechnic Institute, Troy, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-3477-1439","affiliations":[{"raw_affiliation_string":"Department of ECSE, Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-9743-2034","affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6788,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87188458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"44","issue":"12","first_page":"8812","last_page":"8824"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9495999813079834,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9491000175476074,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.8580396771430969},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7941319942474365},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6384831666946411},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.6226096749305725},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5946063995361328},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5447269082069397},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5441986918449402},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.541333794593811},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4423363208770752},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4374277889728546},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4311460554599762},{"id":"https://openalex.org/keywords/adaptive-learning","display_name":"Adaptive learning","score":0.41865813732147217},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3982263505458832},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3795205354690552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28782957792282104},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24111366271972656},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19929641485214233},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.152337908744812}],"concepts":[{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.8580396771430969},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7941319942474365},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6384831666946411},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.6226096749305725},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5946063995361328},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5447269082069397},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5441986918449402},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.541333794593811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4423363208770752},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4374277889728546},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4311460554599762},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.41865813732147217},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3982263505458832},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3795205354690552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28782957792282104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24111366271972656},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19929641485214233},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.152337908744812},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3119645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3119645","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34648431","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34648431","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G285475101","display_name":null,"funder_award_id":"61932001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3627478391","display_name":null,"funder_award_id":"61906200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4488484741","display_name":null,"funder_award_id":"2018YFB0204300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1512407760","https://openalex.org/W1515851193","https://openalex.org/W1518461880","https://openalex.org/W1522301498","https://openalex.org/W1646707810","https://openalex.org/W2071983464","https://openalex.org/W2101167844","https://openalex.org/W2102962763","https://openalex.org/W2124175081","https://openalex.org/W2134932665","https://openalex.org/W2139418546","https://openalex.org/W2145339207","https://openalex.org/W2146502635","https://openalex.org/W2165131254","https://openalex.org/W2305373430","https://openalex.org/W2395162158","https://openalex.org/W2397240726","https://openalex.org/W2468354762","https://openalex.org/W2785523195","https://openalex.org/W2798888671","https://openalex.org/W2885549115","https://openalex.org/W2886837499","https://openalex.org/W2903382683","https://openalex.org/W2946511237","https://openalex.org/W2947958009","https://openalex.org/W2949382134","https://openalex.org/W2960531549","https://openalex.org/W2963625269","https://openalex.org/W2963698657","https://openalex.org/W2964123095","https://openalex.org/W2996927210","https://openalex.org/W2998050631","https://openalex.org/W3009585715","https://openalex.org/W3037570388","https://openalex.org/W3041202696","https://openalex.org/W3163923442","https://openalex.org/W4287116592","https://openalex.org/W4288602110","https://openalex.org/W4289303772","https://openalex.org/W4298064558","https://openalex.org/W4299802797","https://openalex.org/W6600284362","https://openalex.org/W6630944920","https://openalex.org/W6631190155","https://openalex.org/W6678114464","https://openalex.org/W6681435938","https://openalex.org/W6698158655","https://openalex.org/W6711807133","https://openalex.org/W6712173889","https://openalex.org/W6719911377","https://openalex.org/W6738796088","https://openalex.org/W6743500281","https://openalex.org/W6747620207","https://openalex.org/W6750582509","https://openalex.org/W6751189704","https://openalex.org/W6751658861","https://openalex.org/W6753829172","https://openalex.org/W6753892653","https://openalex.org/W6755618874","https://openalex.org/W6757107679","https://openalex.org/W6758937863","https://openalex.org/W6762191990","https://openalex.org/W6762626082","https://openalex.org/W6763578770","https://openalex.org/W6769081937","https://openalex.org/W6771205511","https://openalex.org/W6780559895","https://openalex.org/W6840506281"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2383312578","https://openalex.org/W1574991376","https://openalex.org/W2473364827","https://openalex.org/W2134042548","https://openalex.org/W2772472730","https://openalex.org/W2964123095","https://openalex.org/W2607053317","https://openalex.org/W395196838"],"abstract_inverted_index":{"This":[0,128],"paper":[1],"revisits":[2],"the":[3,10,18,29,41,45,50,63,78,87,100,110,116,119,125,131,144,148,180,195],"temporal":[4],"difference":[5],"(TD)":[6],"learning":[7,47,65,191],"algorithm":[8,48,66],"for":[9],"policy":[11],"evaluation":[12],"tasks":[13],"in":[14,109,143],"reinforcement":[15,190],"learning.":[16],"Typically,":[17],"performance":[19,181],"of":[20,31,62,89,102,118,134,141,157,167,182,197],"TD(0)":[21,34,46,64,142],"and":[22,49,184],"TD(":[23,168],"\u03bb)":[24,186],"is":[25,81,105,136,171],"very":[26],"sensitive":[27,85],"to":[28,77,86,95,124,173],"choice":[30,88],"stepsizes.":[32,90],"Oftentimes,":[33],"suffers":[35],"from":[36],"slow":[37],"convergence.":[38],"Motivated":[39],"by":[40],"tight":[42],"link":[43],"between":[44],"stochastic":[51,149],"gradient":[52],"methods,":[53],"we":[54,72,92,153,162,178],"develop":[55,163],"a":[56],"provably":[57],"convergent":[58],"adaptive":[59,165],"projected":[60],"variant":[61,166],"with":[67],"linear":[68],"function":[69],"approximation":[70],"that":[71,94,130,140],"term":[73],"AdaTD(0).":[74,158],"In":[75],"contrast":[76],"TD(0),":[79,161],"AdaTD(0)":[80,135,183],"robust":[82],"or":[83],"less":[84],"Analytically,":[91],"establish":[93],"reach":[96],"an":[97,164],"\u03f5":[98],"accuracy,":[99],"number":[101],"iterations":[103],"needed":[104],"[Formula:":[106],"see":[107],"text]":[108],"general":[111],"case,":[112],"where":[113],"\u03c1":[114],"represents":[115],"speed":[117],"underlying":[120],"Markov":[121],"chain":[122],"converges":[123],"stationary":[126],"distribution.":[127],"implies":[129],"iteration":[132],"complexity":[133],"no":[137],"worse":[138],"than":[139],"worst":[145],"case.":[146],"When":[147],"semi-gradients":[150],"are":[151],"sparse,":[152],"provide":[154],"theoretical":[155],"acceleration":[156],"Going":[159],"beyond":[160],"\u03bb),":[169],"which":[170,193],"referred":[172],"as":[174],"AdaTD(":[175,185],"\u03bb).":[176],"Empirically,":[177],"evaluate":[179],"on":[187],"several":[188],"standard":[189],"tasks,":[192],"demonstrate":[194],"effectiveness":[196],"our":[198],"new":[199],"approaches.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}