{"id":"https://openalex.org/W3118861484","doi":"https://doi.org/10.1007/s10994-020-05912-5","title":"Concentration bounds for temporal difference learning with linear function approximation: the case of batch data and uniform sampling","display_name":"Concentration bounds for temporal difference learning with linear function approximation: the case of batch data and uniform sampling","publication_year":2021,"publication_date":"2021-01-04","ids":{"openalex":"https://openalex.org/W3118861484","doi":"https://doi.org/10.1007/s10994-020-05912-5","mag":"3118861484"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-020-05912-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-020-05912-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-020-05912-5.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-020-05912-5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068379567","display_name":"L. A. Prashanth","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"L. A. Prashanth","raw_affiliation_strings":["Indian Institute of Technology Madras, Chennai, India"],"raw_orcid":"https://orcid.org/0000-0003-0362-6730","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078138294","display_name":"Nathaniel Korda","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nathaniel Korda","raw_affiliation_strings":["Oxford University, Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006533777","display_name":"R\u00e9mi Munos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R\u00e9mi Munos","raw_affiliation_strings":["Google Deepmind, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Deepmind, Paris, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068379567"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":1.4359,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81603102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"110","issue":"3","first_page":"559","last_page":"618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9991999864578247,"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/T13553","display_name":"Age of Information Optimization","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.6419845819473267},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.5855953693389893},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.504257082939148},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4857805073261261},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4814164340496063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44806280732154846},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.44715118408203125},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.43148547410964966},{"id":"https://openalex.org/keywords/least-squares-function-approximation","display_name":"Least-squares function approximation","score":0.4185195863246918},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4105243384838104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39932751655578613},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3575112223625183},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.29658663272857666},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14656126499176025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13643896579742432},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.10814419388771057},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.09108161926269531},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.09063118696212769}],"concepts":[{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6419845819473267},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.5855953693389893},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.504257082939148},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4857805073261261},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4814164340496063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44806280732154846},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.44715118408203125},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.43148547410964966},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.4185195863246918},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4105243384838104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39932751655578613},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3575112223625183},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.29658663272857666},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14656126499176025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13643896579742432},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.10814419388771057},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.09108161926269531},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.09063118696212769},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-020-05912-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-020-05912-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-020-05912-5.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-020-05912-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-020-05912-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-020-05912-5.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3118861484.pdf","grobid_xml":"https://content.openalex.org/works/W3118861484.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W50486269","https://openalex.org/W177710793","https://openalex.org/W359568995","https://openalex.org/W594357522","https://openalex.org/W1499021337","https://openalex.org/W1505731132","https://openalex.org/W1778554682","https://openalex.org/W1964211927","https://openalex.org/W1989260982","https://openalex.org/W1994616650","https://openalex.org/W2007382693","https://openalex.org/W2071983464","https://openalex.org/W2072931156","https://openalex.org/W2075268401","https://openalex.org/W2086161653","https://openalex.org/W2104753538","https://openalex.org/W2105739999","https://openalex.org/W2105875671","https://openalex.org/W2112420033","https://openalex.org/W2121863487","https://openalex.org/W2125001944","https://openalex.org/W2126410641","https://openalex.org/W2130599357","https://openalex.org/W2138909795","https://openalex.org/W2139050893","https://openalex.org/W2139418546","https://openalex.org/W2148825261","https://openalex.org/W2156737235","https://openalex.org/W2156779765","https://openalex.org/W2159930037","https://openalex.org/W2165418472","https://openalex.org/W2165536370","https://openalex.org/W2235056388","https://openalex.org/W2395162158","https://openalex.org/W2404385938","https://openalex.org/W2798579099","https://openalex.org/W2798888671","https://openalex.org/W2806157618","https://openalex.org/W2912099989","https://openalex.org/W2949257336","https://openalex.org/W2963520461","https://openalex.org/W2964112359","https://openalex.org/W2964123095","https://openalex.org/W2966734222","https://openalex.org/W4211030719","https://openalex.org/W4214717370","https://openalex.org/W4243772471","https://openalex.org/W4285719527","https://openalex.org/W4301435544","https://openalex.org/W6638026421","https://openalex.org/W6640275985","https://openalex.org/W6640533243","https://openalex.org/W6677916085","https://openalex.org/W6683195989","https://openalex.org/W6987391319"],"related_works":["https://openalex.org/W4308702637","https://openalex.org/W2149418961","https://openalex.org/W4286899070","https://openalex.org/W3206576350","https://openalex.org/W4323366756","https://openalex.org/W2772472730","https://openalex.org/W3207830353","https://openalex.org/W4285259204","https://openalex.org/W3008618380","https://openalex.org/W2964123095"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}