{"id":"https://openalex.org/W4286306553","doi":"https://doi.org/10.23919/ascc56756.2022.9828357","title":"Multi-agent cooperative strategy learning method based on transfer Learning","display_name":"Multi-agent cooperative strategy learning method based on transfer Learning","publication_year":2022,"publication_date":"2022-05-04","ids":{"openalex":"https://openalex.org/W4286306553","doi":"https://doi.org/10.23919/ascc56756.2022.9828357"},"language":"en","primary_location":{"id":"doi:10.23919/ascc56756.2022.9828357","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ascc56756.2022.9828357","pdf_url":null,"source":{"id":"https://openalex.org/S4363607827","display_name":"2022 13th Asian Control Conference (ASCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th Asian Control Conference (ASCC)","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/A5025520145","display_name":"Beinuo Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Beinuo Huang","raw_affiliation_strings":["China University of Geoscience,School of Automation,Wuhan,P. R. China","School of Automation, China University of Geoscience, Wuhan, P. R. China"],"affiliations":[{"raw_affiliation_string":"China University of Geoscience,School of Automation,Wuhan,P. R. China","institution_ids":["https://openalex.org/I3124059619"]},{"raw_affiliation_string":"School of Automation, China University of Geoscience, Wuhan, P. R. China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363046","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0001-9924-6833"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["China University of Geoscience,School of Automation,Wuhan,P. R. China","School of Automation, China University of Geoscience, Wuhan, P. R. China"],"affiliations":[{"raw_affiliation_string":"China University of Geoscience,School of Automation,Wuhan,P. R. China","institution_ids":["https://openalex.org/I3124059619"]},{"raw_affiliation_string":"School of Automation, China University of Geoscience, Wuhan, P. R. China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029733518","display_name":"Yipu Sun","orcid":"https://orcid.org/0000-0003-4868-1506"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yipu Sun","raw_affiliation_strings":["China University of Geoscience,School of Automation,Wuhan,P. R. China","School of Automation, China University of Geoscience, Wuhan, P. R. China"],"affiliations":[{"raw_affiliation_string":"China University of Geoscience,School of Automation,Wuhan,P. R. China","institution_ids":["https://openalex.org/I3124059619"]},{"raw_affiliation_string":"School of Automation, China University of Geoscience, Wuhan, P. R. China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039369571","display_name":"Wenpeng He","orcid":"https://orcid.org/0000-0002-1064-741X"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenpeng He","raw_affiliation_strings":["China University of Geoscience,School of Automation,Wuhan,P. R. China","School of Automation, China University of Geoscience, Wuhan, P. R. China"],"affiliations":[{"raw_affiliation_string":"China University of Geoscience,School of Automation,Wuhan,P. R. China","institution_ids":["https://openalex.org/I3124059619"]},{"raw_affiliation_string":"School of Automation, China University of Geoscience, Wuhan, P. R. China","institution_ids":["https://openalex.org/I3124059619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025520145"],"corresponding_institution_ids":["https://openalex.org/I3124059619"],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66941392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1095","last_page":"1100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9894000291824341,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.978600025177002,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8829525709152222},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7697170972824097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6643240451812744},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6490124464035034},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5726984739303589},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5540600419044495},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5142752528190613},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.45979779958724976},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.44624772667884827},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4429120421409607},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.08051976561546326},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.07481932640075684}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8829525709152222},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7697170972824097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6643240451812744},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6490124464035034},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5726984739303589},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5540600419044495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5142752528190613},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.45979779958724976},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.44624772667884827},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4429120421409607},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.08051976561546326},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.07481932640075684},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/ascc56756.2022.9828357","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ascc56756.2022.9828357","pdf_url":null,"source":{"id":"https://openalex.org/S4363607827","display_name":"2022 13th Asian Control Conference (ASCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th Asian Control Conference (ASCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322186","display_name":"Natural Science Foundation of Hubei Province","ror":null},{"id":"https://openalex.org/F4320326707","display_name":"State Grid Corporation of China","ror":"https://ror.org/05twwhs70"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W106607908","https://openalex.org/W2068669811","https://openalex.org/W2146041446","https://openalex.org/W2155336942","https://openalex.org/W2163650400","https://openalex.org/W2165698076","https://openalex.org/W2550023823","https://openalex.org/W2588074036","https://openalex.org/W2772821814","https://openalex.org/W2940479485","https://openalex.org/W2968780774","https://openalex.org/W3081130731","https://openalex.org/W3192537824"],"related_works":["https://openalex.org/W3148138296","https://openalex.org/W4294873804","https://openalex.org/W3153786280","https://openalex.org/W2808546214","https://openalex.org/W3127551068","https://openalex.org/W2152445738","https://openalex.org/W3119422923","https://openalex.org/W2171128163","https://openalex.org/W225045806","https://openalex.org/W1502839564"],"abstract_inverted_index":{"Path":[0],"planning":[1],"is":[2,43,57,99],"of":[3,28,45],"great":[4],"significance":[5],"for":[6],"industrial":[7],"production":[8],"and":[9,59,93,105,121],"daily":[10],"life,":[11],"where":[12],"various":[13],"intelligent":[14],"methods":[15,117],"have":[16],"been":[17],"applied":[18,100],"to":[19,70,101],"it.":[20],"Reinforcement":[21],"learning":[22,53,86,91],"(RL),":[23],"as":[24],"a":[25,82],"popular":[26,48],"area":[27],"machine":[29],"learning,":[30],"can":[31],"effectively":[32],"find":[33],"the":[34,40,46,51,68,102,106,110,114],"optimal":[35],"path":[36],"by":[37,88],"interacting":[38],"with":[39],"environment.":[41],"Q-learning":[42,56,116],"one":[44],"most":[47],"algorithms":[49],"among":[50],"reinforcement":[52],"methods.":[54],"Although":[55],"simple":[58],"effective,":[60],"its":[61],"training":[62],"time":[63],"will":[64],"rise":[65],"sharply":[66],"when":[67],"environment":[69],"be":[71],"explored":[72],"becomes":[73],"complex.":[74],"To":[75],"solve":[76],"this":[77,79],"problem,":[78],"paper":[80],"proposes":[81],"multi-agent":[83],"cooperative":[84],"strategy":[85],"method":[87,98,112],"combining":[89],"transfer":[90],"(TL)":[92],"traditional":[94],"Q-learning.":[95],"The":[96],"proposed":[97,111],"maze":[103],"game":[104],"experiments":[107],"show":[108],"that":[109],"outperforms":[113],"existing":[115],"in":[118],"both":[119],"iterations":[120],"performance.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}