{"id":"https://openalex.org/W3204293975","doi":"https://doi.org/10.1007/s13235-023-00490-2","title":"Robustness and Sample Complexity of Model-Based MARL for General-Sum Markov Games","display_name":"Robustness and Sample Complexity of Model-Based MARL for General-Sum Markov Games","publication_year":2023,"publication_date":"2023-01-21","ids":{"openalex":"https://openalex.org/W3204293975","doi":"https://doi.org/10.1007/s13235-023-00490-2","mag":"3204293975"},"language":"en","primary_location":{"id":"doi:10.1007/s13235-023-00490-2","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1007/s13235-023-00490-2","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/A5088879436","display_name":"Jayakumar Subramanian","orcid":"https://orcid.org/0000-0003-4621-2677"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jayakumar Subramanian","raw_affiliation_strings":["Media and Data Science Research Lab, Digital Experience Cloud, Adobe Inc., Noida, Uttar Pradesh, India"],"raw_orcid":"https://orcid.org/0000-0003-4621-2677","affiliations":[{"raw_affiliation_string":"Media and Data Science Research Lab, Digital Experience Cloud, Adobe Inc., Noida, Uttar Pradesh, India","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056718779","display_name":"Amit Kumar Sinha","orcid":"https://orcid.org/0000-0002-1681-0580"},"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":"Amit Sinha","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005770424","display_name":"Aditya Mahajan","orcid":"https://orcid.org/0000-0001-8125-1191"},"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":"Aditya Mahajan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8125-1191","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088879436"],"corresponding_institution_ids":["https://openalex.org/I1306409833"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.3408,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62411568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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/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"}},"topics":[{"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/T11031","display_name":"Game Theory and Applications","score":0.9941999912261963,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9937999844551086,"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/markov-chain","display_name":"Markov chain","score":0.6903901100158691},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6561618447303772},{"id":"https://openalex.org/keywords/markov-kernel","display_name":"Markov kernel","score":0.48843637108802795},{"id":"https://openalex.org/keywords/markov-perfect-equilibrium","display_name":"Markov perfect equilibrium","score":0.4755261242389679},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.46306461095809937},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4278416335582733},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.4202340841293335},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.41947492957115173},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37243854999542236},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.37073075771331787},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.32042932510375977},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.21043193340301514},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.19942551851272583},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10685065388679504}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6903901100158691},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6561618447303772},{"id":"https://openalex.org/C106666656","wikidata":"https://www.wikidata.org/wiki/Q6771323","display_name":"Markov kernel","level":5,"score":0.48843637108802795},{"id":"https://openalex.org/C67091656","wikidata":"https://www.wikidata.org/wiki/Q6771328","display_name":"Markov perfect equilibrium","level":3,"score":0.4755261242389679},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.46306461095809937},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4278416335582733},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.4202340841293335},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.41947492957115173},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37243854999542236},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.37073075771331787},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.32042932510375977},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.21043193340301514},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.19942551851272583},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10685065388679504}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s13235-023-00490-2","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1007/s13235-023-00490-2","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_s13235-023-00490-2","is_oa":false,"landing_page_url":"http://link.springer.com/10.1007/s13235-023-00490-2","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":[],"awards":[{"id":"https://openalex.org/G7691816131","display_name":null,"funder_award_id":"CFPMN2-30","funder_id":"https://openalex.org/F4320330045","funder_display_name":"Minist\u00e8re de la D\u00e9fense Nationale"}],"funders":[{"id":"https://openalex.org/F4320330045","display_name":"Minist\u00e8re de la D\u00e9fense Nationale","ror":"https://ror.org/035rreb34"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W107583932","https://openalex.org/W165595137","https://openalex.org/W1481965470","https://openalex.org/W1491843047","https://openalex.org/W1496590343","https://openalex.org/W1515072779","https://openalex.org/W1542941925","https://openalex.org/W1570963478","https://openalex.org/W1579118835","https://openalex.org/W1603412719","https://openalex.org/W1608527539","https://openalex.org/W1656130220","https://openalex.org/W1907356258","https://openalex.org/W1964382689","https://openalex.org/W1968518705","https://openalex.org/W1973039793","https://openalex.org/W1985349224","https://openalex.org/W2009543467","https://openalex.org/W2024437990","https://openalex.org/W2026309037","https://openalex.org/W2064778949","https://openalex.org/W2098432798","https://openalex.org/W2099618002","https://openalex.org/W2103561211","https://openalex.org/W2107217702","https://openalex.org/W2116799033","https://openalex.org/W2120678009","https://openalex.org/W2122701159","https://openalex.org/W2129241738","https://openalex.org/W2135949932","https://openalex.org/W2145943204","https://openalex.org/W2154374772","https://openalex.org/W2156268532","https://openalex.org/W2328111639","https://openalex.org/W2329216500","https://openalex.org/W2487793673","https://openalex.org/W2498694880","https://openalex.org/W2575731723","https://openalex.org/W2589394640","https://openalex.org/W2793317277","https://openalex.org/W2890347272","https://openalex.org/W2911300280","https://openalex.org/W2953708620","https://openalex.org/W2964191473","https://openalex.org/W2981452619","https://openalex.org/W2991046523","https://openalex.org/W3029338183","https://openalex.org/W3037361954","https://openalex.org/W3046692137","https://openalex.org/W3093458824","https://openalex.org/W3106398159","https://openalex.org/W3121224226","https://openalex.org/W3122476699","https://openalex.org/W3123512697","https://openalex.org/W3123995372","https://openalex.org/W3193101426","https://openalex.org/W3204192621","https://openalex.org/W3209163867","https://openalex.org/W4231051514","https://openalex.org/W4243848901","https://openalex.org/W4255086963","https://openalex.org/W4285719527","https://openalex.org/W6600474606","https://openalex.org/W6606404423","https://openalex.org/W6724929198"],"related_works":["https://openalex.org/W1520319263","https://openalex.org/W2735859191","https://openalex.org/W3123502079","https://openalex.org/W2987631717","https://openalex.org/W190459708","https://openalex.org/W2950347722","https://openalex.org/W2989366387","https://openalex.org/W2393621008","https://openalex.org/W4309408553","https://openalex.org/W2540690809"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}