{"id":"https://openalex.org/W4391800770","doi":"https://doi.org/10.48550/arxiv.2402.07082","title":"Refined Sample Complexity for Markov Games with Independent Linear Function Approximation","display_name":"Refined Sample Complexity for Markov Games with Independent Linear Function Approximation","publication_year":2024,"publication_date":"2024-02-11","ids":{"openalex":"https://openalex.org/W4391800770","doi":"https://doi.org/10.48550/arxiv.2402.07082"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2402.07082","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.07082","pdf_url":"https://arxiv.org/pdf/2402.07082","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.07082","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104075629","display_name":"Yan Dai","orcid":"https://orcid.org/0000-0001-8004-0309"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dai, Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027905775","display_name":"Qiwen Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Qiwen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033061754","display_name":"Simon S. Du","orcid":"https://orcid.org/0000-0003-0056-8299"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Simon S.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104075629"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9664000272750854,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9664000272750854,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9539999961853027,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9103000164031982,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/sample-complexity","display_name":"Sample complexity","score":0.6912938356399536},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6388249397277832},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6048852205276489},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5354371666908264},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.512290358543396},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.46784934401512146},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3677440285682678},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.310546338558197},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2306499183177948},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13304787874221802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12898054718971252}],"concepts":[{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6912938356399536},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6388249397277832},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6048852205276489},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5354371666908264},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.512290358543396},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.46784934401512146},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3677440285682678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.310546338558197},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2306499183177948},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13304787874221802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12898054718971252},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2402.07082","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.07082","pdf_url":"https://arxiv.org/pdf/2402.07082","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.07082","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.07082","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.07082","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.07082","pdf_url":"https://arxiv.org/pdf/2402.07082","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308668","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60"},{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391800770.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1660242800","https://openalex.org/W2964179321","https://openalex.org/W2077211377","https://openalex.org/W3152686072","https://openalex.org/W1006270037","https://openalex.org/W2607437843","https://openalex.org/W4295700147","https://openalex.org/W2963162727","https://openalex.org/W2106714532","https://openalex.org/W4297979791"],"abstract_inverted_index":{"Markov":[0],"Games":[1],"(MG)":[2],"is":[3,32,93],"an":[4,121],"important":[5],"model":[6],"for":[7],"Multi-Agent":[8],"Reinforcement":[9],"Learning":[10],"(MARL).":[11],"It":[12],"was":[13],"long":[14],"believed":[15],"that":[16,177],"the":[17,22,28,54,59,86,100,112,131,162,168,174,179,184],"\"curse":[18],"of":[19,30,56,78,88,123,130,138,164,181],"multi-agents\"":[20],"(i.e.,":[21,126],"algorithmic":[23],"performance":[24],"drops":[25],"exponentially":[26],"with":[27,106,120,145],"number":[29,87],"agents)":[31],"unavoidable":[33],"until":[34],"several":[35],"recent":[36],"works":[37,52],"(Daskalakis":[38],"et":[39,43,47,117],"al.,":[40,44,48],"2023;":[41,45],"Cui":[42],"Wang":[46,116],"2023).":[49],"While":[50],"these":[51],"resolved":[53],"curse":[55,180],"multi-agents,":[57,182],"when":[58,99],"state":[60],"spaces":[61],"are":[62,69],"prohibitively":[63],"large":[64],"and":[65,189],"(linear)":[66],"function":[67,148],"approximations":[68],"deployed,":[70],"they":[71],"either":[72],"had":[73],"a":[74,82,135],"slower":[75],"convergence":[76,187],"rate":[77],"$O(T^{-1/4})$":[79],"or":[80],"brought":[81],"polynomial":[83],"dependency":[84,192],"on":[85],"actions":[89],"$A_{\\max}$":[90],"--":[91],"which":[92],"avoidable":[94],"in":[95],"single-agent":[96,169],"cases":[97],"even":[98],"loss":[101],"functions":[102],"can":[103],"arbitrarily":[104],"vary":[105],"time.":[107],"This":[108],"paper":[109],"first":[110,175],"refines":[111],"AVLPR":[113],"framework":[114],"by":[115],"al.":[118],"(2023),":[119],"insight":[122],"designing":[124],"*data-dependent*":[125],"stochastic)":[127],"pessimistic":[128],"estimation":[129,159],"sub-optimality":[132],"gap,":[133],"allowing":[134],"broader":[136],"choice":[137],"plug-in":[139],"algorithms.":[140],"When":[141],"specialized":[142],"to":[143,155],"MGs":[144],"independent":[146],"linear":[147],"approximations,":[149],"we":[150,172],"propose":[151],"novel":[152],"*action-dependent":[153],"bonuses*":[154],"cover":[156],"occasionally":[157],"extreme":[158],"errors.":[160],"With":[161],"help":[163],"state-of-the-art":[165],"techniques":[166],"from":[167],"RL":[170],"literature,":[171],"give":[173],"algorithm":[176],"tackles":[178],"attains":[183],"optimal":[185],"$O(T^{-1/2})$":[186],"rate,":[188],"avoids":[190],"$\\text{poly}(A_{\\max})$":[191],"simultaneously.":[193]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2024-02-14T00:00:00"}