{"id":"https://openalex.org/W3201885656","doi":"https://doi.org/10.1007/s10458-023-09599-5","title":"Online Markov decision processes with non-oblivious strategic adversary","display_name":"Online Markov decision processes with non-oblivious strategic adversary","publication_year":2023,"publication_date":"2023-01-27","ids":{"openalex":"https://openalex.org/W3201885656","doi":"https://doi.org/10.1007/s10458-023-09599-5","mag":"3201885656"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-023-09599-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-023-09599-5","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.03604","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081829933","display_name":"Le Cong Dinh","orcid":"https://orcid.org/0000-0002-3306-0603"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Le Cong Dinh","raw_affiliation_strings":["University of Southampton, Southampton, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Southampton, Southampton, United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006156363","display_name":"David Mguni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Henry Mguni","raw_affiliation_strings":["Huawei R &D, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Huawei R &D, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Long Tran-Thanh","orcid":null},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Long Tran-Thanh","raw_affiliation_strings":["University of Warwick, Coventry, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Warwick, Coventry, United Kingdom","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384906","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-0350-2570"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["University College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University College London, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090073634","display_name":"Yaodong Yang","orcid":"https://orcid.org/0000-0001-8132-5613"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaodong Yang","raw_affiliation_strings":["Institute for AI, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for AI, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081829933"],"corresponding_institution_ids":["https://openalex.org/I43439940"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.2483,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53022874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"37","issue":"1","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":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9979000091552734,"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/regret","display_name":"Regret","score":0.7444403171539307},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6505014896392822},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.6252557635307312},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.5522539019584656},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5182569026947021},{"id":"https://openalex.org/keywords/binary-logarithm","display_name":"Binary logarithm","score":0.47847363352775574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47227180004119873},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4677693247795105},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.442624032497406},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.43438467383384705},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4147893488407135},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4102247953414917},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3856719732284546},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3293980360031128},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.26613950729370117},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11279913783073425},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0872407853603363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07882845401763916}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7444403171539307},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6505014896392822},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6252557635307312},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.5522539019584656},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5182569026947021},{"id":"https://openalex.org/C63553672","wikidata":"https://www.wikidata.org/wiki/Q581168","display_name":"Binary logarithm","level":2,"score":0.47847363352775574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47227180004119873},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4677693247795105},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.442624032497406},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43438467383384705},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4147893488407135},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4102247953414917},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3856719732284546},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3293980360031128},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.26613950729370117},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11279913783073425},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0872407853603363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07882845401763916},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10458-023-09599-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-023-09599-5","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2110.03604","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.03604","pdf_url":"https://arxiv.org/pdf/2110.03604","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:eprints.soton.ac.uk:474212","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.soton.ac.uk/474212/1/JAAMAS_Online_Markov_Decision_Processes.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10164563","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10164563/","pdf_url":"https://discovery.ucl.ac.uk/10164563/1/2110.03604.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"   Autonomous Agents and Multi-Agent Systems , 37  (1)    , Article 15. (2023)      ","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.03604","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.03604","pdf_url":"https://arxiv.org/pdf/2110.03604","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W301143384","https://openalex.org/W1570963478","https://openalex.org/W1579184372","https://openalex.org/W1594650099","https://openalex.org/W1849095486","https://openalex.org/W2000850397","https://openalex.org/W2067050450","https://openalex.org/W2074680702","https://openalex.org/W2075567596","https://openalex.org/W2077723394","https://openalex.org/W2101379030","https://openalex.org/W2103315867","https://openalex.org/W2103437045","https://openalex.org/W2106887613","https://openalex.org/W2113351146","https://openalex.org/W2121863487","https://openalex.org/W2131376880","https://openalex.org/W2156211713","https://openalex.org/W2157016390","https://openalex.org/W2209913494","https://openalex.org/W2318394716","https://openalex.org/W2322316662","https://openalex.org/W2569183985","https://openalex.org/W2575731723","https://openalex.org/W2752024324","https://openalex.org/W2765094320","https://openalex.org/W2811481615","https://openalex.org/W2863175877","https://openalex.org/W2894677249","https://openalex.org/W2951945213","https://openalex.org/W2963111827","https://openalex.org/W2963147599","https://openalex.org/W2964067523","https://openalex.org/W2982316857","https://openalex.org/W2990138404","https://openalex.org/W3016722131","https://openalex.org/W3039913305","https://openalex.org/W3043098219","https://openalex.org/W3107615218","https://openalex.org/W3121815827","https://openalex.org/W3137572139","https://openalex.org/W3143788344","https://openalex.org/W3166490809","https://openalex.org/W3169871130","https://openalex.org/W3171362638","https://openalex.org/W3193711978","https://openalex.org/W3196699797","https://openalex.org/W3198396204","https://openalex.org/W3204192621","https://openalex.org/W4211108990","https://openalex.org/W4231611411","https://openalex.org/W4287813665","https://openalex.org/W4289754473","https://openalex.org/W4292022450","https://openalex.org/W4307661072","https://openalex.org/W4324105296","https://openalex.org/W6635459934","https://openalex.org/W6677916085","https://openalex.org/W6790335100"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W1850488217","https://openalex.org/W4287102143","https://openalex.org/W2945119207","https://openalex.org/W3182614517"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
