{"id":"https://openalex.org/W3154967695","doi":"https://doi.org/10.1109/tai.2021.3111142","title":"Deep Q-Learning: Theoretical Insights From an Asymptotic Analysis","display_name":"Deep Q-Learning: Theoretical Insights From an Asymptotic Analysis","publication_year":2021,"publication_date":"2021-09-13","ids":{"openalex":"https://openalex.org/W3154967695","doi":"https://doi.org/10.1109/tai.2021.3111142","mag":"3154967695"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2021.3111142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2021.3111142","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.10870","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086784011","display_name":"Arunselvan Ramaswamy","orcid":"https://orcid.org/0000-0001-7547-8111"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Arunselvan Ramaswamy","raw_affiliation_strings":["Department of Computer Science, Paderborn University, Paderborn, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059439673","display_name":"Eyke H\u00fcllermeier","orcid":"https://orcid.org/0000-0002-9944-4108"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eyke H\u00fcllermeier","raw_affiliation_strings":["Institute of Informatics, University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086784011"],"corresponding_institution_ids":["https://openalex.org/I206945453"],"apc_list":null,"apc_paid":null,"fwci":0.14110358,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51781538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":"2","first_page":"139","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7315540313720703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.688835859298706},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.672198474407196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6704900860786438},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6101878881454468},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5879722237586975},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5220851302146912},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.507770836353302},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5030948519706726},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48743513226509094},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.48575475811958313},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.46322324872016907},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4400615096092224}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7315540313720703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.688835859298706},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.672198474407196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6704900860786438},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6101878881454468},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5879722237586975},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5220851302146912},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.507770836353302},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5030948519706726},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48743513226509094},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.48575475811958313},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.46322324872016907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4400615096092224},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tai.2021.3111142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2021.3111142","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2008.10870","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.10870","pdf_url":"https://arxiv.org/pdf/2008.10870","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3154967695","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.10870","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.10870","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.10870","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.10870","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.10870","pdf_url":"https://arxiv.org/pdf/2008.10870","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3154967695.pdf","grobid_xml":"https://content.openalex.org/works/W3154967695.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W584400962","https://openalex.org/W1967474913","https://openalex.org/W1997394097","https://openalex.org/W2132565565","https://openalex.org/W2145339207","https://openalex.org/W2169071224","https://openalex.org/W2766447205","https://openalex.org/W2802739963","https://openalex.org/W2907626093","https://openalex.org/W2964547635","https://openalex.org/W2970999177","https://openalex.org/W2994937904","https://openalex.org/W3035204268","https://openalex.org/W3198028948","https://openalex.org/W4214855591","https://openalex.org/W4232753567","https://openalex.org/W4238852866","https://openalex.org/W4245376853","https://openalex.org/W4248266115","https://openalex.org/W4297329999","https://openalex.org/W6684921986","https://openalex.org/W6760724441","https://openalex.org/W6767434776","https://openalex.org/W6771404325","https://openalex.org/W6771753067","https://openalex.org/W6784646865","https://openalex.org/W6785328086"],"related_works":["https://openalex.org/W3200856852","https://openalex.org/W2970247852","https://openalex.org/W2766196653","https://openalex.org/W2766346350","https://openalex.org/W2886184427","https://openalex.org/W2990401320","https://openalex.org/W3100578635","https://openalex.org/W2363057055","https://openalex.org/W2954745523","https://openalex.org/W2953192376","https://openalex.org/W1545241636","https://openalex.org/W2954334142","https://openalex.org/W3099499532","https://openalex.org/W1585271355","https://openalex.org/W2962785728","https://openalex.org/W3039502308","https://openalex.org/W2161485371","https://openalex.org/W2944663278","https://openalex.org/W4226026608","https://openalex.org/W3026111743"],"abstract_inverted_index":{"Deep":[0,16,66,136],"Q-Learning":[1,67],"is":[2],"an":[3,77],"important":[4,78],"reinforcement":[5],"learning":[6,92,150],"algorithm,":[7,85],"which":[8],"involves":[9],"training":[10],"a":[11,39,52,58,62],"deep":[12,149],"neural":[13],"network,":[14],"called":[15],"Q-Network":[17],"(DQN),":[18],"to":[19,146],"approximate":[20],"the":[21,48,81,84,87,91,103,133],"well-known":[22],"Q-function.":[23],"Although":[24],"wildly":[25],"successful":[26],"under":[27,68],"laboratory":[28],"conditions,":[29],"serious":[30],"gaps":[31],"between":[32],"theory":[33,142],"and":[34,70,105],"practice":[35],"as":[36,38,111],"well":[37],"lack":[40],"of":[41,61,65,83,90,102,132],"formal":[42],"guarantees":[43],"prevent":[44],"its":[45],"use":[46],"in":[47],"real":[49],"world.":[50],"Adopting":[51],"dynamical":[53],"systems":[54],"perspective,":[55],"we":[56,75,138],"provide":[57],"theoretical":[59],"analysis":[60,121],"popular":[63],"version":[64],"realistic":[69],"verifiable":[71],"assumptions.":[72],"More":[73],"specifically,":[74],"prove":[76],"result":[79,95],"on":[80,98,135],"convergence":[82],"characterizing":[86],"asymptotic":[88],"behavior":[89],"process.":[93],"Our":[94],"sheds":[96],"light":[97],"hitherto":[99],"unexplained":[100],"properties":[101],"algorithm":[104],"helps":[106],"understand":[107,147],"empirical":[108],"observations,":[109],"such":[110],"performance":[112],"inconsistencies":[113],"even":[114],"after":[115],"training.":[116],"Unlike":[117],"previous":[118],"theories,":[119],"our":[120,141],"accommodates":[122],"state":[123],"Markov":[124],"processes":[125],"with":[126],"multiple":[127],"stationary":[128],"distributions.":[129],"In":[130],"spite":[131],"focus":[134],"Q-Learning,":[137],"believe":[139],"that":[140],"may":[143],"be":[144],"applied":[145],"other":[148],"algorithms":[151]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}