{"id":"https://openalex.org/W2135829225","doi":"https://doi.org/10.1109/gamenets.2009.5137416","title":"Online learning in Markov decision processes with arbitrarily changing rewards and transitions","display_name":"Online learning in Markov decision processes with arbitrarily changing rewards and transitions","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2135829225","doi":"https://doi.org/10.1109/gamenets.2009.5137416","mag":"2135829225"},"language":"en","primary_location":{"id":"doi:10.1109/gamenets.2009.5137416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gamenets.2009.5137416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Game Theory for Networks","raw_type":"proceedings-article"},"type":"article","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/A5101868923","display_name":"Jia Yuan Yu","orcid":"https://orcid.org/0000-0002-6674-6150"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jia Yuan Yu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, Canada","Department of Electrical and Computer Engineering, McGill University , Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, Canada","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University , Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036260775","display_name":"Shie Mannor","orcid":"https://orcid.org/0000-0003-4439-7647"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shie Mannor","raw_affiliation_strings":["Department of Electrical and Computer Engineering Department of Electrical Engineering, McGill University, Canada","Department of Electrical and Computer Engineering, McGill University , Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering Department of Electrical Engineering, McGill University, Canada","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University , Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101868923"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":2.4995,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.89843018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2","issue":null,"first_page":"314","last_page":"322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T12288","display_name":"Optimization and Search Problems","score":0.9977999925613403,"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/markov-decision-process","display_name":"Markov decision process","score":0.7448232769966125},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.7338299751281738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6455402970314026},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5839855074882507},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.5788220763206482},{"id":"https://openalex.org/keywords/decision-maker","display_name":"Decision maker","score":0.5523998737335205},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5408099293708801},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5128805637359619},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4941442310810089},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46899914741516113},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.42333418130874634},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41522809863090515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4124367833137512},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.348410427570343},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25623664259910583},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.19984731078147888},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10123604536056519},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08269327878952026}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7448232769966125},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7338299751281738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6455402970314026},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5839855074882507},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.5788220763206482},{"id":"https://openalex.org/C2986080485","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision maker","level":2,"score":0.5523998737335205},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5408099293708801},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5128805637359619},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4941442310810089},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46899914741516113},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.42333418130874634},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41522809863090515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4124367833137512},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.348410427570343},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25623664259910583},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.19984731078147888},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10123604536056519},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08269327878952026},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/gamenets.2009.5137416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gamenets.2009.5137416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Game Theory for Networks","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.325.3304","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.325.3304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cim.mcgill.ca/~jiayuan/olsg.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1496590343","https://openalex.org/W1505937442","https://openalex.org/W1570963478","https://openalex.org/W1576452626","https://openalex.org/W1689445748","https://openalex.org/W1965878388","https://openalex.org/W2074680702","https://openalex.org/W2077902449","https://openalex.org/W2093825590","https://openalex.org/W2098432798","https://openalex.org/W2100110221","https://openalex.org/W2122187689","https://openalex.org/W2127974068","https://openalex.org/W2132775962","https://openalex.org/W2138129780","https://openalex.org/W2156211713","https://openalex.org/W2169401877","https://openalex.org/W2213740169","https://openalex.org/W2334782222","https://openalex.org/W2575731723","https://openalex.org/W4210969899","https://openalex.org/W4285719527","https://openalex.org/W6674961657","https://openalex.org/W6808531524"],"related_works":["https://openalex.org/W4376155396","https://openalex.org/W4287863949","https://openalex.org/W4287102143","https://openalex.org/W1850488217","https://openalex.org/W2945119207","https://openalex.org/W3182614517","https://openalex.org/W4385742498","https://openalex.org/W3041944716","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"We":[0,23,73],"consider":[1],"decision-making":[2],"problems":[3],"in":[4,17,40,56,66,81],"Markov":[5],"decision":[6],"processes":[7],"where":[8,84],"both":[9],"the":[10,13,52,57,64,78,82,85],"rewards":[11,67],"and":[12,30,33,68,93,102],"transition":[14,58,69],"probabilities":[15,70],"vary":[16],"an":[18],"arbitrary":[19],"(e.g.,":[20],"non-stationary)":[21],"fashion.":[22],"present":[24,74],"algorithms":[25],"that":[26,96],"combine":[27],"online":[28],"learning":[29],"robust":[31],"control,":[32],"establish":[34],"guarantees":[35,48],"on":[36,51],"their":[37,45],"performance":[38,101],"evaluated":[39],"retrospect":[41],"against":[42],"alternative":[43],"policies-i.e.,":[44],"regret.":[46],"These":[47],"depend":[49],"critically":[50],"range":[53],"of":[54,63,77],"uncertainty":[55],"probabilities,":[59],"but":[60],"hold":[61],"regardless":[62],"changes":[65],"over":[71],"time.":[72],"a":[75,98],"version":[76,95],"main":[79],"algorithm":[80],"setting":[83],"decision-maker's":[86],"observations":[87],"are":[88],"limited":[89],"to":[90],"its":[91],"trajectory,":[92],"another":[94],"allows":[97],"trade-off":[99],"between":[100],"computational":[103],"complexity.":[104]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}