{"id":"https://openalex.org/W2774591378","doi":"https://doi.org/10.1109/smc.2017.8122916","title":"A shaped-q learning for multi-agents systems","display_name":"A shaped-q learning for multi-agents systems","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2774591378","doi":"https://doi.org/10.1109/smc.2017.8122916","mag":"2774591378"},"language":"en","primary_location":{"id":"doi:10.1109/smc.2017.8122916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2017.8122916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5061189209","display_name":"Kao\u2010Shing Hwang","orcid":"https://orcid.org/0000-0001-9234-4836"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kao-Shing Hwang","raw_affiliation_strings":["Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001081733","display_name":"Wei\u2010Cheng Jiang","orcid":"https://orcid.org/0000-0003-4432-8801"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Cheng Jiang","raw_affiliation_strings":["Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061189209"],"corresponding_institution_ids":["https://openalex.org/I142974352"],"apc_list":null,"apc_paid":null,"fwci":0.195,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64115517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2024","last_page":"2027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9954000115394592,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9925000071525574,"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":0.7190361618995667},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7062246799468994},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6456447839736938},{"id":"https://openalex.org/keywords/bumping","display_name":"Bumping","score":0.6438923478126526},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6304118633270264},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.6133338212966919},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5641404390335083},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5146013498306274},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.47941893339157104},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4662059545516968},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.462089478969574},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4573286771774292},{"id":"https://openalex.org/keywords/intelligent-agent","display_name":"Intelligent agent","score":0.4567382037639618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4540267586708069},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23137959837913513},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13218152523040771},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.08888515830039978},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08130306005477905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190361618995667},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7062246799468994},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6456447839736938},{"id":"https://openalex.org/C2776512755","wikidata":"https://www.wikidata.org/wiki/Q632543","display_name":"Bumping","level":2,"score":0.6438923478126526},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6304118633270264},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.6133338212966919},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5641404390335083},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5146013498306274},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.47941893339157104},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4662059545516968},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.462089478969574},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4573286771774292},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.4567382037639618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4540267586708069},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23137959837913513},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13218152523040771},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.08888515830039978},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08130306005477905},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc.2017.8122916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2017.8122916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W361876","https://openalex.org/W32403112","https://openalex.org/W1557517019","https://openalex.org/W2063033790","https://openalex.org/W2120327309","https://openalex.org/W2121863487","https://openalex.org/W2122481650","https://openalex.org/W3143250040","https://openalex.org/W4214717370","https://openalex.org/W6600018571"],"related_works":["https://openalex.org/W4225571923","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W3096874164","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,49,73,102],"architecture":[4],"where":[5],"each":[6,24],"agent":[7,67,103],"maintains":[8],"a":[9,39,53,58,69,77,105,118,139,154],"cooperative":[10,91,109],"tendency":[11,92,110],"table":[12],"(CTT).":[13],"In":[14,51],"the":[15,36,62,86,98,107,113,164,173,179,184,201],"process":[16,181],"of":[17,35,166,186],"learning,":[18],"agents":[19,37,55,75,134,141,147,199],"need":[20],"not":[21],"communicate":[22],"with":[23,123],"other":[25],"but":[26],"observe":[27],"partners'":[28],"actions":[29,136],"while":[30],"taking":[31,48,72],"actions.":[32],"If":[33],"one":[34,66],"meets":[38],"bad":[40,59],"situation,":[41],"such":[42,52],"as":[43],"bumping":[44],"onto":[45],"obstacles":[46],"after":[47,71],"action.":[50],"case,":[54],"will":[56,130],"receive":[57,138],"reward":[60,79],"from":[61],"environment.":[63],"Similarly,":[64],"if":[65],"reaches":[68],"goal":[70],"action,":[74],"obtain":[76],"good":[78],"instead.":[80],"Rewards":[81],"are":[82,95,115],"used":[83],"to":[84,89,117,152,158,191],"update":[85,142],"policy":[87],"and":[88,112,137,162,182],"adjust":[90],"values":[93],"which":[94],"recorded":[96],"in":[97,127],"individual":[99],"CTT.":[100],"When":[101],"perceives":[104],"state,":[106],"corresponding":[108],"value,":[111],"Q-value":[114],"merged":[116],"Shaped-Q":[119,125],"value.":[120],"The":[121,168],"action":[122],"maximal":[124],"value":[126],"this":[128,150],"state":[129],"be":[131],"selected.":[132],"After":[133],"take":[135],"reward,":[140],"their":[143],"own":[144],"CTTs.":[145],"Therefore,":[146],"could":[148],"use":[149],"method":[151,175],"reach":[153],"consensus":[155],"more":[156,204],"quickly":[157],"enhance":[159],"learning":[160,180],"efficiency":[161],"reduce":[163],"occurrence":[165],"stagnation.":[167],"simulation":[169],"results":[170],"demonstrate":[171],"that":[172],"proposed":[174],"can":[176,197],"speed":[177],"up":[178],"solve":[183],"problem":[185],"huge":[187],"memory":[188],"space":[189],"consumption":[190],"some":[192],"degrees.":[193],"As":[194],"well,":[195],"it":[196],"make":[198],"complete":[200],"task":[202],"together":[203],"efficiently.":[205]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}