{"id":"https://openalex.org/W2085845786","doi":"https://doi.org/10.1109/adprl.2014.7010611","title":"Accelerated gradient temporal difference learning algorithms","display_name":"Accelerated gradient temporal difference learning algorithms","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2085845786","doi":"https://doi.org/10.1109/adprl.2014.7010611","mag":"2085845786"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-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/A5026610704","display_name":"Dominik Meyer","orcid":"https://orcid.org/0000-0002-6948-9858"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Dominik Meyer","raw_affiliation_strings":["Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany","[Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany]"],"affiliations":[{"raw_affiliation_string":"Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"[Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany]","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050128377","display_name":"R\u00e9my Degenne","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Remy Degenne","raw_affiliation_strings":["Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany","[Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany]"],"affiliations":[{"raw_affiliation_string":"Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"[Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany]","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068531475","display_name":"Ahmed Omrane","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ahmed Omrane","raw_affiliation_strings":["Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany","[Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany]"],"affiliations":[{"raw_affiliation_string":"Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"[Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany]","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067323219","display_name":"Hao Shen","orcid":"https://orcid.org/0000-0002-4688-9146"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hao Shen","raw_affiliation_strings":["Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany","[Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany]"],"affiliations":[{"raw_affiliation_string":"Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"[Institute for Data Processing, Technische Universit\u00e4t M\u00fcnchen, Germany]","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026610704"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.48298105,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76117806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"15","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.7407809495925903},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6546424627304077},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6510246992111206},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.5987139344215393},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5960037708282471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5427783131599426},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.539992094039917},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4710920751094818},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43594443798065186},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4250005781650543},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.41063857078552246},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38157689571380615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34127503633499146},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3230517506599426},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2287207841873169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.160732239484787},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.11273622512817383},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.06113076210021973},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.05769869685173035}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7407809495925903},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6546424627304077},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6510246992111206},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.5987139344215393},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5960037708282471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5427783131599426},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.539992094039917},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4710920751094818},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43594443798065186},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4250005781650543},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.41063857078552246},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38157689571380615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34127503633499146},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3230517506599426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2287207841873169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.160732239484787},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.11273622512817383},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.06113076210021973},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.05769869685173035},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2014.7010611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338208","display_name":"International Graduate School of Science and Engineering","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W359568995","https://openalex.org/W1518539242","https://openalex.org/W1597303641","https://openalex.org/W1646707810","https://openalex.org/W1969477885","https://openalex.org/W2075268401","https://openalex.org/W2100677568","https://openalex.org/W2121703796","https://openalex.org/W2139418546","https://openalex.org/W2167302917","https://openalex.org/W2936995161","https://openalex.org/W3041202696","https://openalex.org/W6604254268","https://openalex.org/W6612245137","https://openalex.org/W6635767209","https://openalex.org/W6677984395","https://openalex.org/W6684471329","https://openalex.org/W6761030284"],"related_works":["https://openalex.org/W2947416323","https://openalex.org/W4288346661","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W3008318776","https://openalex.org/W1977633006"],"abstract_inverted_index":{"In":[0,87,151],"this":[1,38,88],"paper":[2],"we":[3,90],"study":[4],"Temporal":[5],"Difference":[6],"(TD)":[7],"Learning":[8],"with":[9,23],"linear":[10,24],"value":[11],"function":[12,25],"approximation.":[13],"The":[14],"classic":[15],"TD":[16,33],"algorithm":[17],"is":[18],"known":[19],"to":[20,50,77,147],"be":[21],"unstable":[22],"approximation":[26],"and":[27,48,107],"off-policy":[28],"learning.":[29],"Recently":[30],"developed":[31,76],"Gradient":[32],"(GTD)":[34],"algorithms":[35,73],"have":[36,74],"addressed":[37],"problem":[39],"successfully.":[40],"Despite":[41],"their":[42],"prominent":[43],"properties":[44],"of":[45,58,115,118],"good":[46],"scalability":[47],"convergence":[49,60],"correct":[51],"solutions,":[52],"they":[53,62],"inherit":[54],"the":[55,100,112,116,119,141,148],"potential":[56],"weakness":[57],"slow":[59],"as":[61],"are":[63],"a":[64,109,123],"stochastic":[65,70,94],"gradient":[66,71,95,117],"descent":[67,72,96],"algorithm.":[68],"Accelerated":[69],"been":[75],"speed":[78],"up":[79],"convergence,":[80],"while":[81],"still":[82],"keeping":[83],"computational":[84],"complexity":[85],"low.":[86],"work,":[89],"develop":[91],"an":[92],"accelerated":[93,129,153],"method":[97],"for":[98,111],"minimizing":[99],"Mean":[101],"Squared":[102],"Projected":[103],"Bellman":[104],"Error":[105],"(MSPBE),":[106],"derive":[108],"bound":[110],"Lipschitz":[113],"constant":[114],"MSPBE,":[120],"which":[121],"plays":[122],"critical":[124],"role":[125],"in":[126,139,145],"our":[127],"proposed":[128],"GTD":[130],"algorithms.":[131,157],"Our":[132],"comprehensive":[133],"numerical":[134],"experiments":[135],"demonstrate":[136],"promising":[137],"performance":[138],"solving":[140],"policy":[142],"evaluation":[143],"problem,":[144],"comparison":[146],"GTD]algorithm":[149],"family.":[150],"particular,":[152],"TDC":[154],"surpasses":[155],"state-of-the-art":[156]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}