{"id":"https://openalex.org/W3034039613","doi":"https://doi.org/10.1109/tit.2021.3120096","title":"Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction","display_name":"Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3034039613","doi":"https://doi.org/10.1109/tit.2021.3120096","mag":"3034039613"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2021.3120096","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tit.2021.3120096","pdf_url":"https://ieeexplore.ieee.org/ielx7/18/9660615/09570295.pdf","source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/18/9660615/09570295.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gen Li","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gen Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA","[Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544 USA.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"[Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544 USA.]","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005015806","display_name":"Yuting Wei","orcid":"https://orcid.org/0000-0003-1488-4647"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuting Wei","raw_affiliation_strings":["Department of Statistics and Data Science, Wharton School, University of Pennsylvania, Philadelphia, PA, USA","[Department of Statistics and Data Science, the Wharton School, University of Pennsylvania, Philadelphia, PA 19104, USA. (e-mail: ytwei@wharton.upenn.edu)]"],"raw_orcid":"https://orcid.org/0000-0003-1488-4647","affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science, Wharton School, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"[Department of Statistics and Data Science, the Wharton School, University of Pennsylvania, Philadelphia, PA 19104, USA. (e-mail: ytwei@wharton.upenn.edu)]","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053809095","display_name":"Yuejie Chi","orcid":"https://orcid.org/0000-0002-6766-5459"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuejie Chi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA,15213, USA"],"raw_orcid":"https://orcid.org/0000-0002-6766-5459","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA,15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuantao Gu","orcid":"https://orcid.org/0000-0002-8427-1021"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuantao Gu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Electronic Engineering; Tsinghua University; Beijing 100084; China"],"raw_orcid":"https://orcid.org/0000-0002-8427-1021","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering; Tsinghua University; Beijing 100084; China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yuxin Chen","orcid":"https://orcid.org/0000-0001-9256-5815"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxin Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA","[Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544 USA.]"],"raw_orcid":"https://orcid.org/0000-0001-9256-5815","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"[Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544 USA.]","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":2.0997,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88972012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"68","issue":"1","first_page":"448","last_page":"473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.14020000398159027,"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":0.14020000398159027,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.10719999670982361,"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/T11804","display_name":"Quantum many-body systems","score":0.10140000283718109,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"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/combinatorics","display_name":"Combinatorics","score":0.6342015266418457},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6280888915061951},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5582430362701416},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5242736339569092},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.49113771319389343},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.46403786540031433},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.42449936270713806},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4195929169654846},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.41353267431259155},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1814223825931549},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17443951964378357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.12221923470497131},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.10190975666046143}],"concepts":[{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.6342015266418457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6280888915061951},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5582430362701416},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5242736339569092},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.49113771319389343},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.46403786540031433},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.42449936270713806},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4195929169654846},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.41353267431259155},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1814223825931549},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17443951964378357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.12221923470497131},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.10190975666046143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tit.2021.3120096","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tit.2021.3120096","pdf_url":"https://ieeexplore.ieee.org/ielx7/18/9660615/09570295.pdf","source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tit.2021.3120096","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tit.2021.3120096","pdf_url":"https://ieeexplore.ieee.org/ielx7/18/9660615/09570295.pdf","source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1469985387","display_name":null,"funder_award_id":"N00014-19-1-2404","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G248161301","display_name":null,"funder_award_id":"IIS-1900140","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G251365076","display_name":null,"funder_award_id":"CCF-2106739","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2590387755","display_name":null,"funder_award_id":"CCF-1806154","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3030967435","display_name":"RI: Medium: Collaborative Research:Algorithmic High-Dimensional Statistics: Optimality, Computtional Barriers, and High-Dimensional Corrections","funder_award_id":"1900140","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3467583470","display_name":null,"funder_award_id":"N00014-19-1-2120","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3582032785","display_name":null,"funder_award_id":"CCF-2007911","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4061742820","display_name":null,"funder_award_id":"FA9550-19-1-0030","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G4558904681","display_name":null,"funder_award_id":"W911NF-20-1-0097","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G4910588663","display_name":null,"funder_award_id":"2106739","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5174315691","display_name":null,"funder_award_id":"2106778","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5359226925","display_name":null,"funder_award_id":"1907661","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G556410599","display_name":null,"funder_award_id":"W911NF-18-1-0303","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5945795592","display_name":null,"funder_award_id":"CCF-1907661","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G630122624","display_name":"RI: Small: Uncertainty Quantification for  Nonconvex Low-Complexity Models","funder_award_id":"2100158","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6566275953","display_name":null,"funder_award_id":"DMS-2015447","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6636086349","display_name":null,"funder_award_id":"2007911","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6788006064","display_name":null,"funder_award_id":"61971266","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6938454608","display_name":null,"funder_award_id":"CCF-2106778","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7060655475","display_name":"Collaborative Research: Fine-Grained Statistical Inference in High Dimension: Actionable Information, Bias Reduction, and Optimality","funder_award_id":"2015447","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8272153555","display_name":"CIF: Medium: Collaborative Research: Nonconvex Optimization for High-Dimensional Signal Estimation: Theory and Fast Algorithms","funder_award_id":"1806154","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G854152385","display_name":null,"funder_award_id":"N00014-18-1-2142","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8597684915","display_name":null,"funder_award_id":"W911NF-18-1-0303","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G86464884","display_name":null,"funder_award_id":"IIS-2100158","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034039613.pdf","grobid_xml":"https://content.openalex.org/works/W3034039613.grobid-xml"},"referenced_works_count":118,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W137538757","https://openalex.org/W568673721","https://openalex.org/W1511694993","https://openalex.org/W1865368880","https://openalex.org/W1999254175","https://openalex.org/W2071983464","https://openalex.org/W2077343054","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2107438106","https://openalex.org/W2114202040","https://openalex.org/W2118686230","https://openalex.org/W2120678009","https://openalex.org/W2122701159","https://openalex.org/W2129670787","https://openalex.org/W2145339207","https://openalex.org/W2147750403","https://openalex.org/W2149166950","https://openalex.org/W2150147323","https://openalex.org/W2165131254","https://openalex.org/W2594203335","https://openalex.org/W2795561155","https://openalex.org/W2890347272","https://openalex.org/W2907626093","https://openalex.org/W2942023420","https://openalex.org/W2942608247","https://openalex.org/W2944956041","https://openalex.org/W2946280430","https://openalex.org/W2949578685","https://openalex.org/W2956123884","https://openalex.org/W2963049774","https://openalex.org/W2963488874","https://openalex.org/W2963616027","https://openalex.org/W2963872309","https://openalex.org/W2964123095","https://openalex.org/W2964299116","https://openalex.org/W2966363432","https://openalex.org/W2970128053","https://openalex.org/W2970650844","https://openalex.org/W2970961807","https://openalex.org/W2970999177","https://openalex.org/W2971723392","https://openalex.org/W2982113767","https://openalex.org/W2990210896","https://openalex.org/W2995519751","https://openalex.org/W2995999665","https://openalex.org/W3003165689","https://openalex.org/W3004163841","https://openalex.org/W3004770624","https://openalex.org/W3005174111","https://openalex.org/W3006052551","https://openalex.org/W3007300954","https://openalex.org/W3011120880","https://openalex.org/W3014860839","https://openalex.org/W3015956888","https://openalex.org/W3029338183","https://openalex.org/W3034741641","https://openalex.org/W3035204268","https://openalex.org/W3038797447","https://openalex.org/W3041182030","https://openalex.org/W3041202696","https://openalex.org/W3046139323","https://openalex.org/W3090826728","https://openalex.org/W3099303842","https://openalex.org/W3105602917","https://openalex.org/W3121342653","https://openalex.org/W3129308573","https://openalex.org/W3136514496","https://openalex.org/W3136903997","https://openalex.org/W3203759272","https://openalex.org/W3206149081","https://openalex.org/W4233061323","https://openalex.org/W4233696721","https://openalex.org/W4245577611","https://openalex.org/W4297329999","https://openalex.org/W6605726098","https://openalex.org/W6639926649","https://openalex.org/W6676105031","https://openalex.org/W6678494045","https://openalex.org/W6681795105","https://openalex.org/W6734234284","https://openalex.org/W6748232849","https://openalex.org/W6750027077","https://openalex.org/W6752725515","https://openalex.org/W6754906582","https://openalex.org/W6757677476","https://openalex.org/W6758937863","https://openalex.org/W6761964196","https://openalex.org/W6762191990","https://openalex.org/W6762653638","https://openalex.org/W6763048320","https://openalex.org/W6763257922","https://openalex.org/W6763948599","https://openalex.org/W6765092683","https://openalex.org/W6766156165","https://openalex.org/W6767092952","https://openalex.org/W6767434776","https://openalex.org/W6771556211","https://openalex.org/W6771753067","https://openalex.org/W6771824692","https://openalex.org/W6773126427","https://openalex.org/W6773140934","https://openalex.org/W6773415824","https://openalex.org/W6773605947","https://openalex.org/W6773637655","https://openalex.org/W6774582792","https://openalex.org/W6775686901","https://openalex.org/W6775935937","https://openalex.org/W6776530296","https://openalex.org/W6777828934","https://openalex.org/W6779539656","https://openalex.org/W6780553864","https://openalex.org/W6780969776","https://openalex.org/W6784003830","https://openalex.org/W6785038382","https://openalex.org/W6790768012","https://openalex.org/W6791074358"],"related_works":["https://openalex.org/W9910182","https://openalex.org/W46930346","https://openalex.org/W10389882","https://openalex.org/W30550639","https://openalex.org/W5493544","https://openalex.org/W47489483","https://openalex.org/W25883607","https://openalex.org/W7548172","https://openalex.org/W12860732","https://openalex.org/W14837077"],"abstract_inverted_index":{"Asynchronous":[0],"Q-learning":[1,81],"aims":[2],"to":[3,89,132,217],"learn":[4],"the":[5,66,84,103,110,164,168,174,184,188,196,200,206,210,214,226,233,237,242,296,299],"optimal":[6],"action-value":[7],"function":[8],"(or":[9],"Q-function)":[10],"of":[11,22,78,86,102,112,173,180,199,213,248,266,315],"a":[12,19,27,32,138,219,246,264],"Markov":[13],"decision":[14],"process":[15],"(MDP),":[16],"based":[17],"on":[18,31,109,298],"single":[20],"trajectory":[21,216],"Markovian":[23,215],"samples":[24,87,193],"induced":[25],"by":[26,245,263,313],"behavior":[28],"policy.":[29],"Focusing":[30],"<inline-formula":[33,45,55,67,93,113,146,154,251,269,284,302],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[34,46,56,68,94,114,147,155,252,270,285,303],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[35,47,57,69,95,115,148,156,253,271,286,304],"<tex-math":[36,48,58,70,96,116,149,157,254,272,287,305],"notation=\"LaTeX\">$\\gamma":[37],"$":[38,98,289],"</tex-math></inline-formula>":[39,51,61,74,99,130,152,161,258,277,290,309],"-discounted":[40],"MDP":[41],"with":[42,191],"state":[43],"space":[44,54],"notation=\"LaTeX\">$\\mathcal":[49,59],"{S}$":[50],"and":[52,153,167,229,262],"action":[53],"{A}$":[60],",":[62],"we":[63,293],"demonstrate":[64,294],"that":[65,137,295],"notation=\"LaTeX\">$\\ell":[71],"_{\\infty":[72],"}$":[73,308],"-based":[75],"sample":[76,175,185],"complexity":[77,186],"classical":[79],"asynchronous":[80],"\u2014":[82,105],"namely,":[83],"number":[85],"needed":[88],"yield":[90],"an":[91],"entrywise":[92],"notation=\"LaTeX\">$\\varepsilon":[97,288],"-accurate":[100],"estimate":[101],"Q-function":[104],"is":[106,143,223],"at":[107,225,249,267],"most":[108],"order":[111],"notation=\"LaTeX\">$\\frac":[117,306],"{1}{":[118],"\\mu":[119,127],"_{\\mathsf":[120,128,159],"{min}}(1-\\gamma)^{5}\\varepsilon":[121],"^{2}}+":[122],"\\frac":[123],"{":[124],"t_{\\mathsf":[125],"{mix}}}{":[126],"{min}}(1-\\gamma)}$":[129],"up":[131],"some":[133],"logarithmic":[134],"factor,":[135],"provided":[136],"proper":[139],"constant":[140],"learning":[141],"rate":[142],"adopted.":[144],"Here,":[145],"notation=\"LaTeX\">$t_{\\mathsf":[150,273],"{mix}}$":[151],"notation=\"LaTeX\">$\\mu":[158],"{min}}$":[160],"denote":[162],"respectively":[163],"mixing":[165],"time":[166],"minimum":[169],"state-action":[170],"occupancy":[171],"probability":[172],"trajectory.":[176,201],"The":[177,202],"first":[178],"term":[179,204],"this":[181],"bound":[182,239],"matches":[183],"in":[187],"synchronous":[189],"case":[190],"independent":[192],"drawn":[194],"from":[195],"stationary":[197],"distribution":[198,212],"second":[203],"reflects":[205],"cost":[207],"taken":[208],"for":[209,259,278],"empirical":[211],"reach":[218],"steady":[220],"state,":[221],"which":[222],"incurred":[224],"very":[227],"beginning":[228],"becomes":[230],"amortized":[231],"as":[232],"algorithm":[234],"runs.":[235],"Encouragingly,":[236],"above":[238],"improves":[240],"upon":[241],"state-of-the-art":[243],"result":[244],"factor":[247,265],"least":[250,268],"notation=\"LaTeX\">$|\\mathcal":[255],"{S}||\\mathcal":[256,275],"{A}|$":[257,276],"all":[260],"scenarios,":[261],"{mix}}|\\mathcal":[274],"any":[279],"sufficiently":[280],"small":[281],"accuracy":[282],"level":[283],".":[291],"Further,":[292],"scaling":[297],"effective":[300],"horizon":[301],"{1}{1-\\gamma":[307],"can":[310],"be":[311],"improved":[312],"means":[314],"variance":[316],"reduction.":[317]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2020-06-12T00:00:00"}