{"id":"https://openalex.org/W2156956168","doi":"https://doi.org/10.1109/tai.2002.1180839","title":"Cooperative co-learning: a model-based approach for solving multi-agent reinforcement problems","display_name":"Cooperative co-learning: a model-based approach for solving multi-agent reinforcement problems","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2156956168","doi":"https://doi.org/10.1109/tai.2002.1180839","mag":"2156956168"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2002.1180839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2002.1180839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5032281855","display_name":"Bruno Scherrer","orcid":"https://orcid.org/0000-0001-6097-4489"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"B. Scherrer","raw_affiliation_strings":["B\u00e2timent LORIA, LORIA INRIA-Lorraine, Vandoeuvre-les-Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"B\u00e2timent LORIA, LORIA INRIA-Lorraine, Vandoeuvre-les-Nancy, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210121838"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051052976","display_name":"Fran\u00e7ois Charpillet","orcid":"https://orcid.org/0000-0001-8260-1536"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"F. Charpillet","raw_affiliation_strings":["B\u00e2timent LORIA, LORIA INRIA-Lorraine, Vandoeuvre-les-Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"B\u00e2timent LORIA, LORIA INRIA-Lorraine, Vandoeuvre-les-Nancy, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210121838"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.26937013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"463","last_page":"468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9490000009536743,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8303450345993042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7127346396446228},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4668691158294678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41867485642433167},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12821966409683228}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8303450345993042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127346396446228},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4668691158294678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41867485642433167},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12821966409683228},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tai.2002.1180839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2002.1180839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:inria-00100814v1","is_oa":false,"landing_page_url":"https://inria.hal.science/inria-00100814","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"14th IEEE International Conference on Tools with Artificial Intelligence - ICTAI 2002, 2002, Washington, USA, 6 p","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W6242441","https://openalex.org/W1484740474","https://openalex.org/W1563317173","https://openalex.org/W1657542410","https://openalex.org/W1993412827","https://openalex.org/W2128477394","https://openalex.org/W2137647991","https://openalex.org/W2334782222","https://openalex.org/W2543115189","https://openalex.org/W2984808340","https://openalex.org/W6600231840","https://openalex.org/W6628916341","https://openalex.org/W6672490383","https://openalex.org/W6678016301","https://openalex.org/W6679104208","https://openalex.org/W6827038600"],"related_works":["https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W4319773215","https://openalex.org/W4224287422","https://openalex.org/W2952472710","https://openalex.org/W4255994452","https://openalex.org/W4206669594","https://openalex.org/W3005560120","https://openalex.org/W3037422413","https://openalex.org/W2959276766"],"abstract_inverted_index":{"Solving":[0],"multiagent":[1,14],"reinforcement":[2],"learning":[3],"problems":[4],"is":[5,26],"a":[6,37,46,71],"key":[7],"issue.":[8],"Indeed,":[9],"the":[10,24,30,56,59],"complexity":[11],"of":[12,23,32,48,61],"deriving":[13],"plans,":[15],"especially":[16],"when":[17],"one":[18,44],"uses":[19],"an":[20],"explicit":[21],"model":[22],"problem,":[25],"dramatically":[27],"increasing":[28],"with":[29],"number":[31],"agents.":[33],"This":[34],"papers":[35],"introduces":[36],"general":[38,72],"iterative":[39],"heuristic:":[40],"at":[41],"each":[42],"step":[43],"chooses":[45],"sub-group":[47],"agents":[49,62],"and":[50,74,90],"update":[51],"their":[52],"policies":[53],"to":[54,81],"optimize":[55],"task":[57],"given":[58],"rest":[60],"have":[63],"fixed":[64],"plans.":[65],"We":[66],"analyse":[67],"this":[68],"process":[69],"in":[70],"purpose":[73],"show":[75],"how":[76],"it":[77],"can":[78],"be":[79],"applied":[80],"Markov":[82,87,94],"decision":[83,88,95],"processes,":[84],"partially":[85,92],"observable":[86,93],"processes":[89],"decentralized":[91],"processes.":[96]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}