{"id":"https://openalex.org/W3020125231","doi":"https://doi.org/10.5555/1756006.1859902","title":"Near-optimal Regret Bounds for Reinforcement Learning","display_name":"Near-optimal Regret Bounds for Reinforcement Learning","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W3020125231","doi":"https://doi.org/10.5555/1756006.1859902","mag":"3020125231"},"language":"en","primary_location":{"id":"mag:3020125231","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/1756006.1859902","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research","raw_type":null},"type":"article","indexed_in":[],"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/A5077640675","display_name":"JakschThomas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"JakschThomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012665306","display_name":"OrtnerRonald","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"OrtnerRonald","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005791629","display_name":"AuerPeter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"AuerPeter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7211,"has_fulltext":false,"cited_by_count":212,"citation_normalized_percentile":{"value":0.9485785,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9876999855041504,"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":0.9876999855041504,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9836000204086304,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9484000205993652,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8878917098045349},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7713931202888489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5873591303825378},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47631630301475525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4708140790462494},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3253290057182312},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31190112233161926}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8878917098045349},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7713931202888489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5873591303825378},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47631630301475525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4708140790462494},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3253290057182312},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31190112233161926}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3020125231","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/1756006.1859902","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Journal of Machine Learning Research","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2406016125","https://openalex.org/W2970347269","https://openalex.org/W2465145931","https://openalex.org/W3116886558","https://openalex.org/W2071815241","https://openalex.org/W2512014291","https://openalex.org/W3182076562","https://openalex.org/W2489939061","https://openalex.org/W2971936494","https://openalex.org/W3037646606","https://openalex.org/W3009923408","https://openalex.org/W2981289360","https://openalex.org/W2123447947","https://openalex.org/W1626977535","https://openalex.org/W2178643644","https://openalex.org/W2156211713","https://openalex.org/W3176362036","https://openalex.org/W3037645935","https://openalex.org/W50090763","https://openalex.org/W3209366948"],"abstract_inverted_index":{"For":[0],"undiscounted":[1],"reinforcement":[2],"learning":[3,16],"in":[4],"Markov":[5],"decision":[6],"processes":[7],"(MDPs)":[8],"we":[9],"consider":[10],"the":[11,28],"total":[12],"regret":[13],"of":[14],"a":[15],"algorithm":[17],"with":[18],"respect":[19],"to":[20,26],"an":[21],"optimal":[22],"policy.":[23],"In":[24],"order":[25],"describe":[27],"transiti...":[29]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":58},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":3}],"updated_date":"2025-10-10T17:16:08.811792","created_date":"2025-10-10T00:00:00"}