{"id":"https://openalex.org/W2115393638","doi":"https://doi.org/10.1109/irds.2002.1041500","title":"Fast reinforcement learning approach to cooperative behavior acquisition in multi-agent system","display_name":"Fast reinforcement learning approach to cooperative behavior acquisition in multi-agent system","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2115393638","doi":"https://doi.org/10.1109/irds.2002.1041500","mag":"2115393638"},"language":"en","primary_location":{"id":"doi:10.1109/irds.2002.1041500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/irds.2002.1041500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/RSJ International Conference on Intelligent Robots and System","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/A5101775106","display_name":"Songhao Piao","orcid":"https://orcid.org/0000-0003-4351-9112"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songhao Piao","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Harbin Institute of Technology,,,,,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology,,,,,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102172432","display_name":"Bingrong Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingrong Hong","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Harbin Institute of Technology,,,,,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology,,,,,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4688,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75407801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"871","last_page":"875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9886999726295471,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9304001331329346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7383782863616943},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6311776638031006},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6272854804992676},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5914220809936523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5701618790626526},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5668246746063232},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5596818327903748},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5215001702308655},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4682157039642334},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.434036523103714},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.43337109684944153},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38728880882263184},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32241785526275635},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14740347862243652}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9304001331329346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383782863616943},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6311776638031006},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6272854804992676},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5914220809936523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5701618790626526},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5668246746063232},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5596818327903748},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5215001702308655},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4682157039642334},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.434036523103714},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43337109684944153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38728880882263184},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32241785526275635},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14740347862243652},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/irds.2002.1041500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/irds.2002.1041500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/RSJ International Conference on Intelligent Robots and System","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1499371387","https://openalex.org/W1507326261","https://openalex.org/W1507591516","https://openalex.org/W1542941925","https://openalex.org/W1795214984","https://openalex.org/W2034587361","https://openalex.org/W2097346851","https://openalex.org/W2114153380","https://openalex.org/W2118674046","https://openalex.org/W2120658945","https://openalex.org/W2198041288","https://openalex.org/W2296607379","https://openalex.org/W6629993198","https://openalex.org/W6638104662","https://openalex.org/W6677207121"],"related_works":["https://openalex.org/W4213119504","https://openalex.org/W1882507001","https://openalex.org/W2364169244","https://openalex.org/W2557694176","https://openalex.org/W3205824709","https://openalex.org/W3170446423","https://openalex.org/W4319083788","https://openalex.org/W3022038857","https://openalex.org/W1981165078","https://openalex.org/W2115393638"],"abstract_inverted_index":{"In":[0,34],"multi-agent":[1],"robotic":[2],"systems,":[3],"the":[4,18,76,78,88,94,99,105,113,124,127],"overlap":[5],"of":[6,59,118,126],"actions":[7],"selected":[8],"by":[9,111],"each":[10],"agent":[11,31,47],"results":[12,117],"in":[13],"poor":[14],"cooperation,":[15],"while,":[16],"at":[17],"same":[19],"time,":[20],"conventional":[21],"reinforcement":[22,60,79],"learning":[23,61,80,95,106],"entails":[24],"a":[25,39,49,71,83],"large":[26],"computational":[27],"cost":[28],"because":[29],"every":[30],"must":[32],"learn.":[33],"this":[35],"paper,":[36],"we":[37],"propose":[38],"novel":[40],"method":[41,101],"to":[42,52,102],"solve":[43],"these":[44],"problems.":[45],"The":[46,116],"uses":[48],"rule":[50,90],"set":[51],"conduct":[53],"its":[54],"behavior.":[55],"Our":[56],"system":[57],"consists":[58],"with":[62],"an":[63],"Action":[64],"Selection":[65],"Priority":[66],"Level":[67],"(ASPL)":[68],"module":[69,81,91],"and":[70,120],"generalized":[72,89],"rules":[73],"module.":[74],"Using":[75],"ASPL,":[77],"chooses":[82],"proper":[84],"cooperative":[85],"behavior":[86],"while":[87],"can":[92,108],"accelerate":[93],"process.":[96],"By":[97],"applying":[98],"proposed":[100,128],"robot":[103],"soccer,":[104],"process":[107],"be":[109],"accelerated":[110],"reducing":[112],"search":[114],"space.":[115],"simulation":[119],"real":[121],"experiments":[122],"indicate":[123],"effectiveness":[125],"method.":[129]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}