{"id":"https://openalex.org/W4386811917","doi":"https://doi.org/10.1007/978-3-031-43421-1_26","title":"On the\u00a0Distributional Convergence of\u00a0Temporal Difference Learning","display_name":"On the\u00a0Distributional Convergence of\u00a0Temporal Difference Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386811917","doi":"https://doi.org/10.1007/978-3-031-43421-1_26"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-43421-1_26","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-43421-1_26","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5076673098","display_name":"Jie Dai","orcid":"https://orcid.org/0000-0001-9848-6894"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Dai","raw_affiliation_strings":["Changsha, China"],"affiliations":[{"raw_affiliation_string":"Changsha, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101799909","display_name":"Xuguang Chen","orcid":"https://orcid.org/0000-0002-4191-7750"},"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":true,"raw_author_name":"Xuguang Chen","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101799909"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3386599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"439","last_page":"454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.979200005531311,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7710013389587402},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.7197356224060059},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6783868670463562},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6668176651000977},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5924874544143677},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5838179588317871},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5550616979598999},{"id":"https://openalex.org/keywords/preconditioner","display_name":"Preconditioner","score":0.5408440828323364},{"id":"https://openalex.org/keywords/stationary-distribution","display_name":"Stationary distribution","score":0.5207536220550537},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.511788547039032},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46007686853408813},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4405193328857422},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.43453580141067505},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4177316427230835},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4114410877227783},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38105154037475586},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2972240746021271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24343425035476685},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.16048818826675415},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1450413167476654},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1295899748802185},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.12920784950256348},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.06750982999801636}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7710013389587402},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.7197356224060059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783868670463562},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6668176651000977},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5924874544143677},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5838179588317871},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5550616979598999},{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.5408440828323364},{"id":"https://openalex.org/C98951983","wikidata":"https://www.wikidata.org/wiki/Q7604341","display_name":"Stationary distribution","level":3,"score":0.5207536220550537},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.511788547039032},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46007686853408813},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4405193328857422},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.43453580141067505},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4177316427230835},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4114410877227783},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38105154037475586},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2972240746021271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24343425035476685},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.16048818826675415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1450413167476654},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1295899748802185},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.12920784950256348},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.06750982999801636},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"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:10.1007/978-3-031-43421-1_26","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-43421-1_26","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W615510159","https://openalex.org/W1646707810","https://openalex.org/W1970997001","https://openalex.org/W1973754217","https://openalex.org/W1990585910","https://openalex.org/W1994616650","https://openalex.org/W2049659086","https://openalex.org/W2139418546","https://openalex.org/W2480611454","https://openalex.org/W2964123095","https://openalex.org/W3041202696","https://openalex.org/W3043072433","https://openalex.org/W3092741379","https://openalex.org/W3206576350","https://openalex.org/W3210074665","https://openalex.org/W4233762729","https://openalex.org/W6639101836","https://openalex.org/W6649218630","https://openalex.org/W6851591039"],"related_works":["https://openalex.org/W2357336958","https://openalex.org/W4281839678","https://openalex.org/W2535797495","https://openalex.org/W152950973","https://openalex.org/W2300963337","https://openalex.org/W2283235658","https://openalex.org/W3162287216","https://openalex.org/W2108077990","https://openalex.org/W2058487055","https://openalex.org/W2963398804"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}