{"id":"https://openalex.org/W3205079722","doi":"https://doi.org/10.1007/s13235-021-00420-0","title":"Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games","display_name":"Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games","publication_year":2022,"publication_date":"2022-01-05","ids":{"openalex":"https://openalex.org/W3205079722","doi":"https://doi.org/10.1007/s13235-021-00420-0","mag":"3205079722"},"language":"en","primary_location":{"id":"doi:10.1007/s13235-021-00420-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13235-021-00420-0","pdf_url":null,"source":{"id":"https://openalex.org/S2502731256","display_name":"Dynamic Games and Applications","issn_l":"2153-0785","issn":["2153-0785","2153-0793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320186","host_organization_name":"Birkh\u00e4user","host_organization_lineage":["https://openalex.org/P4310320186","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Birkh\u00e4user","Springer Science+Business Media"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dynamic Games and Applications","raw_type":"journal-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/A5069765568","display_name":"Weichao Mao","orcid":"https://orcid.org/0000-0001-8301-4173"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weichao Mao","raw_affiliation_strings":["Coordinated Science Laboratory, Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, 61801, USA"],"raw_orcid":"https://orcid.org/0000-0001-8301-4173","affiliations":[{"raw_affiliation_string":"Coordinated Science Laboratory, Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019604570","display_name":"Tamer Ba\u015far","orcid":"https://orcid.org/0000-0003-4406-7875"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamer Ba\u015far","raw_affiliation_strings":["Coordinated Science Laboratory, Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, 61801, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Coordinated Science Laboratory, Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069765568"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":3.0511,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91413134,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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/T11031","display_name":"Game Theory and Applications","score":0.993399977684021,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7941263914108276},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.7099384665489197},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.626284658908844},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5835002660751343},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5828729867935181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5760732293128967},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5506198406219482},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.47049829363822937},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4455660581588745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4079837203025818},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3466026484966278},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.32473814487457275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2827894389629364},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1229633092880249},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08782395720481873}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7941263914108276},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7099384665489197},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.626284658908844},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5835002660751343},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5828729867935181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5760732293128967},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5506198406219482},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.47049829363822937},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4455660581588745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4079837203025818},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3466026484966278},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.32473814487457275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2827894389629364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1229633092880249},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08782395720481873}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s13235-021-00420-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13235-021-00420-0","pdf_url":null,"source":{"id":"https://openalex.org/S2502731256","display_name":"Dynamic Games and Applications","issn_l":"2153-0785","issn":["2153-0785","2153-0793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320186","host_organization_name":"Birkh\u00e4user","host_organization_lineage":["https://openalex.org/P4310320186","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Birkh\u00e4user","Springer Science+Business Media"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dynamic Games and Applications","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:spr:dyngam:v:13:y:2023:i:1:d:10.1007_s13235-021-00420-0","is_oa":false,"landing_page_url":"http://link.springer.com/10.1007/s13235-021-00420-0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G303160554","display_name":null,"funder_award_id":"ONR MURI Grant N00014-16-1-2710","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5659316339","display_name":null,"funder_award_id":"AFOSR Grant FA9550-19-1-0353","funder_id":"https://openalex.org/F4320332467","funder_display_name":"U.S. Air Force"}],"funders":[{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W585548487","https://openalex.org/W1496590343","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1570963478","https://openalex.org/W1626977535","https://openalex.org/W1726806267","https://openalex.org/W1850488217","https://openalex.org/W1967250398","https://openalex.org/W1977655452","https://openalex.org/W1988716172","https://openalex.org/W1991888757","https://openalex.org/W1997147068","https://openalex.org/W2002373723","https://openalex.org/W2057913812","https://openalex.org/W2088956500","https://openalex.org/W2092025421","https://openalex.org/W2104602264","https://openalex.org/W2116067849","https://openalex.org/W2118929276","https://openalex.org/W2120846115","https://openalex.org/W2123827275","https://openalex.org/W2126776273","https://openalex.org/W2145067550","https://openalex.org/W2148825261","https://openalex.org/W2164637474","https://openalex.org/W2257979135","https://openalex.org/W2530849036","https://openalex.org/W2575731723","https://openalex.org/W2773381986","https://openalex.org/W2951371685","https://openalex.org/W2962990479","https://openalex.org/W2963049774","https://openalex.org/W2963111827","https://openalex.org/W2963326510","https://openalex.org/W2963763894","https://openalex.org/W2964191473","https://openalex.org/W2972782056","https://openalex.org/W2982316857","https://openalex.org/W3033089188","https://openalex.org/W3034189935","https://openalex.org/W3035454135","https://openalex.org/W3037361954","https://openalex.org/W3046553904","https://openalex.org/W3082483631","https://openalex.org/W3083441818","https://openalex.org/W3100292177","https://openalex.org/W3100785954","https://openalex.org/W3111119344","https://openalex.org/W3131948096","https://openalex.org/W3166490809","https://openalex.org/W3167472281","https://openalex.org/W4206742934","https://openalex.org/W4244096180","https://openalex.org/W4254547512","https://openalex.org/W4285719527","https://openalex.org/W4301435544","https://openalex.org/W6600140940"],"related_works":["https://openalex.org/W4287863949","https://openalex.org/W1850488217","https://openalex.org/W4287102143","https://openalex.org/W2945119207","https://openalex.org/W3182614517","https://openalex.org/W2808418668","https://openalex.org/W2970347269","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W3096874164"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
