{"id":"https://openalex.org/W2742783667","doi":"https://doi.org/10.1145/3108421.3108434","title":"Research of Multi-Agent Cognition and Decision","display_name":"Research of Multi-Agent Cognition and Decision","publication_year":2017,"publication_date":"2017-06-14","ids":{"openalex":"https://openalex.org/W2742783667","doi":"https://doi.org/10.1145/3108421.3108434","mag":"2742783667"},"language":"en","primary_location":{"id":"doi:10.1145/3108421.3108434","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3108421.3108434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 International Conference on E-commerce, E-Business and E-Government","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":null,"display_name":"Liu Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu Dong","raw_affiliation_strings":["Science and Technology on Complex Electronic, System Simulation Laboratory, Equipment academy, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Complex Electronic, System Simulation Laboratory, Equipment academy, Beijing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100870796","display_name":"Yan xuefei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan xuefei","raw_affiliation_strings":["Science and Technology on Complex Electronic, System Simulation Laboratory, Equipment academy, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Complex Electronic, System Simulation Laboratory, Equipment academy, Beijing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100688676","display_name":"Xinming Li","orcid":"https://orcid.org/0000-0003-1861-5751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Xinming","raw_affiliation_strings":["Science and Technology on Complex Electronic, System Simulation Laboratory, Equipment academy, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Complex Electronic, System Simulation Laboratory, Equipment academy, Beijing","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010662241","display_name":"Wang Shoubiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang Shoubiao","raw_affiliation_strings":["Science and Technology on Complex Electronic, System Simulation Laboratory, Equipment academy, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Complex Electronic, System Simulation Laboratory, Equipment academy, Beijing","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09770405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9746999740600586,"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":0.9746999740600586,"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/T13832","display_name":"Advanced Decision-Making Techniques","score":0.9488999843597412,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9467999935150146,"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":0.8994512557983398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6290191411972046},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5674142241477966},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.561090350151062},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5441944599151611},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5150842070579529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4899446368217468},{"id":"https://openalex.org/keywords/decision-theory","display_name":"Decision theory","score":0.4776688516139984},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.4650823473930359},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.45240503549575806},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4508110284805298},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.3641100227832794},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.21484726667404175},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18082672357559204},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14200946688652039},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11760598421096802},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.1064189076423645},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08422467112541199}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8994512557983398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6290191411972046},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5674142241477966},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.561090350151062},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5441944599151611},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5150842070579529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4899446368217468},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.4776688516139984},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.4650823473930359},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.45240503549575806},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4508110284805298},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3641100227832794},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.21484726667404175},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18082672357559204},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14200946688652039},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11760598421096802},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.1064189076423645},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08422467112541199},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3108421.3108434","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3108421.3108434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 International Conference on E-commerce, E-Business and E-Government","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W28019117","https://openalex.org/W32403112","https://openalex.org/W38737181","https://openalex.org/W71768770","https://openalex.org/W791343330","https://openalex.org/W1513468570","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1564534945","https://openalex.org/W1577829257","https://openalex.org/W1589364763","https://openalex.org/W1700690958","https://openalex.org/W1712734637","https://openalex.org/W1716473942","https://openalex.org/W1923869523","https://openalex.org/W1970587001","https://openalex.org/W1973069320","https://openalex.org/W1980164457","https://openalex.org/W1983587899","https://openalex.org/W2004550196","https://openalex.org/W2019906898","https://openalex.org/W2031692836","https://openalex.org/W2032069808","https://openalex.org/W2040849554","https://openalex.org/W2041483866","https://openalex.org/W2042560356","https://openalex.org/W2044863546","https://openalex.org/W2051832248","https://openalex.org/W2056509413","https://openalex.org/W2062306811","https://openalex.org/W2066972285","https://openalex.org/W2070963703","https://openalex.org/W2073264034","https://openalex.org/W2083535091","https://openalex.org/W2134134797","https://openalex.org/W2140609521","https://openalex.org/W2149722565","https://openalex.org/W2152512857","https://openalex.org/W2155626675","https://openalex.org/W2162735718","https://openalex.org/W2165752741","https://openalex.org/W2260779904","https://openalex.org/W2294162370","https://openalex.org/W2397253692","https://openalex.org/W2496782927","https://openalex.org/W3041202696","https://openalex.org/W3139377883","https://openalex.org/W3140951851","https://openalex.org/W3146059362","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2937181779"],"abstract_inverted_index":{"Reinforcement":[0],"Learning(RL)":[1],"is":[2,38,92],"the":[3,18,25,28,32,35,43,50,55,68,77,87,96,101,104,109,112,116,120,125,130],"main":[4],"cognition":[5,97],"and":[6,14,72,90,98,119,142,146],"decision":[7,99,114],"method":[8],"of":[9,34,67,86,103,111,124],"Agent":[10,44],"since":[11,31],"its":[12],"adaptation":[13],"exploration":[15],"ability":[16],"to":[17,60,74],"unknown":[19],"environment,":[20],"but":[21,46],"it":[22],"cannot":[23],"ensure":[24],"convergence":[26],"for":[27,95],"multi-Agent":[29,91,105,126],"situation":[30],"transition":[33],"state":[36],"space":[37],"not":[39],"only":[40],"influenced":[41,48],"by":[42,49],"itself":[45],"also":[47],"other":[51,56,78],"Agent's":[52,57],"action,":[53],"so":[54],"action":[58],"has":[59],"be":[61],"taken":[62],"into":[63],"account.":[64],"In":[65],"consideration":[66],"deep":[69],"theory":[70,89],"foundation":[71],"advantages":[73],"deal":[75],"with":[76,129],"player's":[79],"policy,":[80],"this":[81],"paper":[82],"think":[83],"that":[84],"combination":[85],"games":[88,131],"a":[93],"breakthrough":[94],"in":[100],"status":[102],"Learning.":[106],"Based":[107],"on":[108],"introduction":[110],"traditional":[113],"technology,":[115],"learning":[117,128],"technology":[118],"typical":[121],"algorithm":[122],"framework":[123],"reinforcement":[127],"theory,":[132],"some":[133],"related":[134],"algorithms":[135],"such":[136],"as":[137],"MinMax-Q,":[138],"nash-Q,":[139],"FF-Q,":[140],"CE-Q":[141],"Nego-Q":[143],"were":[144],"presented":[145],"analyzed.":[147]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}