{"id":"https://openalex.org/W2754557139","doi":"https://doi.org/10.20965/jaciii.2017.p0917","title":"Comparison Between Reinforcement Learning Methods with Different Goal Selections in Multi-Agent Cooperation","display_name":"Comparison Between Reinforcement Learning Methods with Different Goal Selections in Multi-Agent Cooperation","publication_year":2017,"publication_date":"2017-09-20","ids":{"openalex":"https://openalex.org/W2754557139","doi":"https://doi.org/10.20965/jaciii.2017.p0917","mag":"2754557139"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.20965/jaciii.2017.p0917","pdf_url":null,"source":{"id":"https://openalex.org/S4511983","display_name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","issn_l":"1883-8014","issn":["1883-8014","1343-0130"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4324309662","host_organization_name":"Fuji Technology Press Ltd.","host_organization_lineage":["https://openalex.org/P4324309662"],"host_organization_lineage_names":["Fuji Technology Press Ltd."],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.20965/jaciii.2017.p0917","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037814625","display_name":"Fumito Uwano","orcid":"https://orcid.org/0000-0003-4139-2605"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fumito Uwano","raw_affiliation_strings":["The Univ. of Electro-Communications#TAB#"],"affiliations":[{"raw_affiliation_string":"The Univ. of Electro-Communications#TAB#","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084452161","display_name":"Keiki Takadama","orcid":"https://orcid.org/0009-0007-0916-5505"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiki Takadama","raw_affiliation_strings":["The Univ. of Electro-Communications#TAB#"],"affiliations":[{"raw_affiliation_string":"The Univ. of Electro-Communications#TAB#","institution_ids":["https://openalex.org/I20529979"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":0,"currency":"USD","value_usd":0,"provenance":"doaj"},"apc_paid":null,"fwci":0.378,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.702919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":75,"max":77},"biblio":{"volume":"21","issue":"5","first_page":"917","last_page":"929"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995,"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":0.9995,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9864,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9654,"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/q-learning","display_name":"Q-learning","score":0.41846204}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.82228434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863041},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5830983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5651562},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.54274637},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4528613},{"id":"https://openalex.org/C181622380","wikidata":"https://www.wikidata.org/wiki/Q26911","display_name":"Profit (economics)","level":2,"score":0.42128697},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.41846204},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.339176},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.058622837},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","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}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.20965/jaciii.2017.p0917","pdf_url":null,"source":{"id":"https://openalex.org/S4511983","display_name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","issn_l":"1883-8014","issn":["1883-8014","1343-0130"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4324309662","host_organization_name":"Fuji Technology Press Ltd.","host_organization_lineage":["https://openalex.org/P4324309662"],"host_organization_lineage_names":["Fuji Technology Press Ltd."],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.20965/jaciii.2017.p0917","pdf_url":null,"source":{"id":"https://openalex.org/S4511983","display_name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","issn_l":"1883-8014","issn":["1883-8014","1343-0130"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4324309662","host_organization_name":"Fuji Technology Press Ltd.","host_organization_lineage":["https://openalex.org/P4324309662"],"host_organization_lineage_names":["Fuji Technology Press Ltd."],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.48,"id":"https://metadata.un.org/sdg/17"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":10,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1542094515","https://openalex.org/W1641379095","https://openalex.org/W1967567143","https://openalex.org/W2037067712","https://openalex.org/W2087322096","https://openalex.org/W2263562440","https://openalex.org/W2407262400","https://openalex.org/W2550023823","https://openalex.org/W3011120880"],"related_works":["https://openalex.org/W4319083788","https://openalex.org/W4289712363","https://openalex.org/W4220782901","https://openalex.org/W4206669594","https://openalex.org/W3022038857","https://openalex.org/W2923653485","https://openalex.org/W2911718261","https://openalex.org/W2784904752","https://openalex.org/W2047937115","https://openalex.org/W20361778"],"abstract_inverted_index":{"This":[0],"study":[1],"discusses":[2],"important":[3,216],"factors":[4],"for":[5,22,29,150],"zero":[6,210],"communication,":[7,211],"multi-agent":[8,30,212],"cooperation":[9,31,153],"by":[10,116],"comparing":[11],"different":[12,26],"modified":[13],"reinforcement":[14],"learning":[15,19,207],"methods.":[16],"The":[17,33,67,142,181],"two":[18,111,158],"methods":[20,159],"used":[21],"comparison":[23],"were":[24],"assigned":[25],"goal":[27,61,100],"selections":[28],"tasks.":[32],"first":[34],"method":[35,69],"is":[36,62,70,96,215],"called":[37,71],"Profit":[38],"Minimizing":[39],"Reinforcement":[40,74],"Learning":[41,75],"(PMRL);":[42],"it":[43,77,214],"forces":[44,78],"agents":[45,79,89,163,179,187,198,219],"to":[46,49,59,64,80,98,102,164,188],"learn":[47,81,189,199],"how":[48],"reach":[50,103],"the":[51,56,60,65,88,93,99,104,110,118,123,126,132,138,147,151,157,162,170,173,176,186,193,197],"farthest":[52],"goal,":[53],"and":[54,86,129,136,175],"then":[55],"agent":[57,94,152],"closest":[58,97,106],"directed":[63],"goal.":[66,107],"second":[68],"Yielding":[72],"Action":[73],"(YARL);":[76],"through":[82],"a":[83,91,203,222],"Q-learning":[84],"process,":[85],"if":[87,169],"have":[90,221],"conflict,":[92],"that":[95,156,217,220],"learns":[101],"next":[105],"To":[108],"compare":[109],"methods,":[112],"we":[113],"designed":[114],"experiments":[115],"adjusting":[117],"following":[119],"maze":[120,148,174],"factors:":[121],"(1)":[122],"location":[124],"of":[125,134,140,172,178,206],"start":[127],"point":[128],"goal;":[130],"(2)":[131],"number":[133,177,205],"agents;":[135],"(3)":[137],"size":[139,171],"maze.":[141],"intensive":[143],"simulations":[144],"performed":[145],"on":[146],"problem":[149],"task":[154],"revealed":[155],"successfully":[160],"enabled":[161],"exhibit":[165],"cooperative":[166,190,200],"behavior,":[167,191],"even":[168],"change.":[180],"PMRL":[182],"mechanism":[183,195],"always":[184],"enables":[185],"whereas":[192],"YARL":[194],"makes":[196],"behavior":[201],"over":[202],"small":[204],"iterations.":[208],"In":[209],"cooperation,":[213],"only":[218],"conflict":[223],"cooperate":[224],"with":[225],"each":[226],"other.":[227]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2754557139","counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2024-12-13T19:47:55.361520","created_date":"2017-09-25"}