{"id":"https://openalex.org/W3158432731","doi":"https://doi.org/10.1109/ciss50987.2021.9400319","title":"Blackwell Online Learning for Markov Decision Processes","display_name":"Blackwell Online Learning for Markov Decision Processes","publication_year":2021,"publication_date":"2021-03-24","ids":{"openalex":"https://openalex.org/W3158432731","doi":"https://doi.org/10.1109/ciss50987.2021.9400319","mag":"3158432731"},"language":"en","primary_location":{"id":"doi:10.1109/ciss50987.2021.9400319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss50987.2021.9400319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 55th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100455256","display_name":"Tao Li","orcid":"https://orcid.org/0000-0001-8966-7239"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["New York University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002380510","display_name":"Guanze Peng","orcid":"https://orcid.org/0000-0003-4474-1129"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanze Peng","raw_affiliation_strings":["New York University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081500464","display_name":"Quanyan Zhu","orcid":"https://orcid.org/0000-0002-0008-2953"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quanyan Zhu","raw_affiliation_strings":["New York University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":2.364,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8931338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.988099992275238,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8438133001327515},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8314990401268005},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.6606253385543823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6210472583770752},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5570053458213806},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5309134721755981},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.48642659187316895},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48507872223854065},{"id":"https://openalex.org/keywords/decision-theory","display_name":"Decision theory","score":0.46291548013687134},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.452846884727478},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.44590723514556885},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.42622876167297363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39853787422180176},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.36792874336242676},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28917503356933594},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22865721583366394}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8438133001327515},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8314990401268005},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.6606253385543823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6210472583770752},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5570053458213806},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5309134721755981},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.48642659187316895},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48507872223854065},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.46291548013687134},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.452846884727478},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.44590723514556885},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.42622876167297363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39853787422180176},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.36792874336242676},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28917503356933594},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22865721583366394},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ciss50987.2021.9400319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss50987.2021.9400319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 55th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5230278422","display_name":null,"funder_award_id":"W911NF-19-1-0041","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G6022798193","display_name":"CPS: Breakthrough: A Meta-Game Theoretic Approach to Cyber-Physical Co-Design of Secure and Resilient Control Systems","funder_award_id":"1544782","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G82235702","display_name":"NUCLEAR ENERGY UNIVERSITY PROGRAMS - NUCLEAR ENERGY UNIVERSITY PROGRAMS CONSOLIDATED INNOVATIVE NUCLEAR RESEARCH - THE OHIO STATE UNIVERSITY","funder_award_id":"DENE0008986","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W594357522","https://openalex.org/W1576452626","https://openalex.org/W1605188341","https://openalex.org/W1871300696","https://openalex.org/W1964757264","https://openalex.org/W1980516134","https://openalex.org/W1982813377","https://openalex.org/W1998587447","https://openalex.org/W2074680702","https://openalex.org/W2077723394","https://openalex.org/W2082261506","https://openalex.org/W2100752967","https://openalex.org/W2115524942","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2126776273","https://openalex.org/W2137766593","https://openalex.org/W2139418546","https://openalex.org/W2145943204","https://openalex.org/W2156211713","https://openalex.org/W2162006934","https://openalex.org/W2168635421","https://openalex.org/W2257979135","https://openalex.org/W2320006964","https://openalex.org/W2334782222","https://openalex.org/W2920763178","https://openalex.org/W2942369252","https://openalex.org/W2985924367","https://openalex.org/W2993995411","https://openalex.org/W3037341449","https://openalex.org/W3115230442","https://openalex.org/W3158432731","https://openalex.org/W4206275166","https://openalex.org/W4240813273","https://openalex.org/W4243772471","https://openalex.org/W4292022450","https://openalex.org/W4302328783","https://openalex.org/W6634528131","https://openalex.org/W6639256633","https://openalex.org/W6681692701","https://openalex.org/W6760385598","https://openalex.org/W6762026818"],"related_works":["https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W4287102143","https://openalex.org/W1850488217","https://openalex.org/W2945119207","https://openalex.org/W3182614517","https://openalex.org/W2152670157","https://openalex.org/W2472051997","https://openalex.org/W4308702637","https://openalex.org/W2386410636"],"abstract_inverted_index":{"Ahstract-This":[0],"work":[1],"provides":[2],"a":[3,52],"novel":[4],"interpretation":[5],"of":[6,24,98],"Markov":[7],"Decision":[8],"Processes":[9],"(MDP)":[10],"from":[11,43],"the":[12,22,25,30,34,44,60,76,105],"online":[13,19,93],"optimization":[14,20],"viewpoint.":[15],"In":[16],"such":[17],"an":[18],"context,":[21],"policy":[23],"MDP":[26],"is":[27,38],"viewed":[28],"as":[29,40],"decision":[31],"variable":[32],"while":[33],"corresponding":[35],"value":[36,83],"function":[37],"treated":[39],"payoff":[41],"feedback":[42],"environment.":[45],"Based":[46,74],"on":[47,75],"this":[48],"interpretation,":[49],"we":[50,79],"construct":[51],"Blackwell":[53,65,82,90],"game":[54],"induced":[55],"by":[56,113],"MDP,":[57,96],"which":[58,99],"bridges":[59],"gap":[61],"among":[62],"regret":[63],"minimization,":[64],"approachability":[66,77],"theory,":[67,78],"and":[68,88],"learning":[69,94],"theory":[70],"for":[71,85,92],"MDP.":[72],"Specifically,":[73],"propose":[80],"1)":[81],"iteration":[84],"offline":[86],"planning":[87],"2)":[89],"Q-learning":[91],"in":[95],"both":[97],"are":[100,111],"shown":[101],"to":[102,104],"converge":[103],"optimal":[106],"solution.":[107],"Our":[108],"theoretical":[109],"guarantees":[110],"corroborated":[112],"numerical":[114],"experiments.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}