{"id":"https://openalex.org/W3045907529","doi":"https://doi.org/10.23919/acc45564.2020.9147428","title":"Finite-Sample Analysis of Distributed Q-learning for Multi-Agent Networks","display_name":"Finite-Sample Analysis of Distributed Q-learning for Multi-Agent Networks","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3045907529","doi":"https://doi.org/10.23919/acc45564.2020.9147428","mag":"3045907529"},"language":"en","primary_location":{"id":"doi:10.23919/acc45564.2020.9147428","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","raw_type":"proceedings-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/A5015690883","display_name":"Paulo Heredia","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paulo Heredia","raw_affiliation_strings":["School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007165145","display_name":"Hasan Ghadialy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138135","display_name":"Northrop Grumman (Germany)","ror":"https://ror.org/043wc6127","country_code":"DE","type":"company","lineage":["https://openalex.org/I2948394018","https://openalex.org/I4210138135"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hasan Ghadialy","raw_affiliation_strings":["Northrop Grumman Corporation"],"affiliations":[{"raw_affiliation_string":"Northrop Grumman Corporation","institution_ids":["https://openalex.org/I4210138135"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070733769","display_name":"Shaoshuai Mou","orcid":"https://orcid.org/0000-0002-3698-4238"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaoshuai Mou","raw_affiliation_strings":["School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015690883"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.1542,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51211857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3511","last_page":"3516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9955999851226807,"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"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9948999881744385,"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/computer-science","display_name":"Computer science","score":0.6493895053863525},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5714634656906128},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5570018291473389},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4329591989517212},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.41090887784957886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3249891400337219},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.1826007068157196},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09769263863563538}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6493895053863525},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5714634656906128},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5570018291473389},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4329591989517212},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41090887784957886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3249891400337219},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.1826007068157196},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09769263863563538},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc45564.2020.9147428","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W6043852","https://openalex.org/W41554520","https://openalex.org/W1155239231","https://openalex.org/W1513468570","https://openalex.org/W1542941925","https://openalex.org/W1560074431","https://openalex.org/W1641379095","https://openalex.org/W1830271598","https://openalex.org/W2085366587","https://openalex.org/W2104602264","https://openalex.org/W2114791779","https://openalex.org/W2119112357","https://openalex.org/W2122701159","https://openalex.org/W2165726932","https://openalex.org/W2167485994","https://openalex.org/W2395575420","https://openalex.org/W2575705757","https://openalex.org/W2592798481","https://openalex.org/W2611028343","https://openalex.org/W2768629321","https://openalex.org/W2788115019","https://openalex.org/W2791173582","https://openalex.org/W2904058351","https://openalex.org/W2911365170","https://openalex.org/W2911706765","https://openalex.org/W2913326990","https://openalex.org/W2914506472","https://openalex.org/W2947012451","https://openalex.org/W2947958009","https://openalex.org/W2951896791","https://openalex.org/W2962856794","https://openalex.org/W2963488874","https://openalex.org/W2964005211","https://openalex.org/W3011120880","https://openalex.org/W3011272463","https://openalex.org/W3153787838","https://openalex.org/W4288279122","https://openalex.org/W4298064558","https://openalex.org/W6600255050","https://openalex.org/W6630520071","https://openalex.org/W6633472260","https://openalex.org/W6638424430","https://openalex.org/W6672070530","https://openalex.org/W6675811377","https://openalex.org/W6678097026","https://openalex.org/W6678494045","https://openalex.org/W6712181171","https://openalex.org/W6734678876","https://openalex.org/W6736572398","https://openalex.org/W6748232849","https://openalex.org/W6749032143","https://openalex.org/W6749379201","https://openalex.org/W6751658861","https://openalex.org/W6751921135","https://openalex.org/W6756813310","https://openalex.org/W6757967233","https://openalex.org/W6760018431","https://openalex.org/W6762191990","https://openalex.org/W6762949467","https://openalex.org/W6766343273","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2320718078","https://openalex.org/W2653530212","https://openalex.org/W1185300216","https://openalex.org/W2953216818","https://openalex.org/W2030191131","https://openalex.org/W2954163146","https://openalex.org/W2123899227","https://openalex.org/W2899086345","https://openalex.org/W2896057011","https://openalex.org/W3188962172"],"abstract_inverted_index":{"We":[0,39],"will":[1,40],"provide":[2,41],"a":[3,10,24,58],"finite-sample":[4],"analysis":[5],"to":[6,87],"the":[7,46,54,66,81,94],"convergence":[8],"of":[9,45,57,68,83],"distributed":[11,72],"algorithm":[12],"for":[13],"Q-learning":[14],"in":[15,18,93],"multi-agent":[16],"systems,":[17],"which":[19,50],"each":[20,84],"agent":[21,85],"is":[22],"assigned":[23],"private":[25],"reward":[26],"function":[27],"and":[28,61,70],"can":[29],"only":[30],"communicate":[31],"with":[32],"its":[33],"nearby":[34],"neighbors":[35],"under":[36],"time-varying":[37],"networks.":[38],"an":[42],"upper":[43],"bound":[44],"average":[47],"squared":[48],"error,":[49],"takes":[51],"into":[52],"account":[53],"time":[55],"evolution":[56],"consensus":[59],"error":[60,82],"does":[62],"not":[63],"rely":[64],"on":[65],"assumption":[67],"independent":[69],"identically":[71],"(i.i.d)":[73],"samples.":[74],"In":[75],"addition,":[76],"our":[77],"results":[78,92],"indicate":[79],"that":[80],"converges":[86],"zero":[88],"asymptotically,":[89],"supporting":[90],"empirical":[91],"literature.":[95]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}