{"id":"https://openalex.org/W2045237457","doi":"https://doi.org/10.1109/sii.2012.6427345","title":"Reinforcement learning approaches for dispersion games","display_name":"Reinforcement learning approaches for dispersion games","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2045237457","doi":"https://doi.org/10.1109/sii.2012.6427345","mag":"2045237457"},"language":"en","primary_location":{"id":"doi:10.1109/sii.2012.6427345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii.2012.6427345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE/SICE International Symposium on System Integration (SII)","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/A5100514055","display_name":"Kazuaki Yamada","orcid":null},"institutions":[{"id":"https://openalex.org/I158123994","display_name":"Toyo University","ror":"https://ror.org/059d6yn51","country_code":"JP","type":"education","lineage":["https://openalex.org/I158123994"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kazuaki Yamada","raw_affiliation_strings":["Department of Mechanical Engineering, Toyo University, Saitama, Japan","Department of Mechanical Engineering, Toyo University, 2100 Kujirai, Kawagoe-shi, Saitama, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Toyo University, Saitama, Japan","institution_ids":["https://openalex.org/I158123994"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Toyo University, 2100 Kujirai, Kawagoe-shi, Saitama, Japan","institution_ids":["https://openalex.org/I158123994"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100514055"],"corresponding_institution_ids":["https://openalex.org/I158123994"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0994157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"102","issue":null,"first_page":"440","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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/T11031","display_name":"Game Theory and Applications","score":0.9728999733924866,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9713000059127808,"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":0.7839269638061523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7388718724250793},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.6102325320243835},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.5910791158676147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5292363166809082},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5253586173057556},{"id":"https://openalex.org/keywords/aliasing","display_name":"Aliasing","score":0.496650755405426},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.46115919947624207},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33708757162094116}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7839269638061523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7388718724250793},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.6102325320243835},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.5910791158676147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5292363166809082},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5253586173057556},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.496650755405426},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.46115919947624207},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33708757162094116},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii.2012.6427345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii.2012.6427345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1541739192","https://openalex.org/W1850545963","https://openalex.org/W1977359924","https://openalex.org/W2014852613","https://openalex.org/W2099618002","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2166078965","https://openalex.org/W4206055737","https://openalex.org/W4214717370","https://openalex.org/W6653928095","https://openalex.org/W7056377967"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W2494202692","https://openalex.org/W2161520603","https://openalex.org/W2612836981","https://openalex.org/W2604958989","https://openalex.org/W2618716983","https://openalex.org/W2620638075","https://openalex.org/W1586030051","https://openalex.org/W2372480026","https://openalex.org/W2066202387"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"new":[3],"reinforcement":[4],"learning":[5,191],"approaches":[6,72],"for":[7,36,49,123],"dispersion":[8],"games":[9],"in":[10,85,181],"multi-agent":[11,42,182],"systems.":[12],"Multi-agent":[13],"systems":[14,18,35,183],"can":[15,144,161],"establish":[16],"orderly":[17],"autonomously":[19],"through":[20,184],"interaction":[21,64],"with":[22,232],"autonomous":[23,185],"agents.":[24,67,192,212],"We":[25,68,139,175],"expect":[26],"to":[27,30,51,56,73,125,129,151,166,172,197],"be":[28],"able":[29],"build":[31],"flexible":[32],"and":[33,88,112,169,226],"robust":[34],"the":[37,70,74,90,93,97,103,113,141,153,177,189,199,202,208,236],"environmental":[38],"changes":[39],"by":[40,63,82,148,206],"using":[41,149,159],"system":[43],"approaches.":[44,239],"However,":[45,119],"it":[46,101,120],"is":[47,102,121],"difficult":[48,122],"designers":[50],"preliminarily":[52],"embed":[53],"appropriate":[54],"behaviors":[55,137,231],"avoid":[57],"conflict":[58,178,229],"because":[59,131],"complex":[60],"dynamics":[61],"emerges":[62],"between":[65],"many":[66,79,190],"apply":[69],"proposed":[71,94],"narrow":[75,86,98],"road":[76,99],"problem":[77],"that":[78,106,143,218],"agents":[80,124,164,170,219],"go":[81,167],"each":[83],"other":[84,114,135],"roads,":[87],"verify":[89],"effectivity":[91],"of":[92,188,201,211,224],"method.":[95],"In":[96,193],"problem,":[100],"optimal":[104],"strategy":[105,128],"an":[107],"agent":[108,115],"selects":[109,116],"going":[110],"forward":[111,168],"giving":[117],"way.":[118,174],"decide":[126],"which":[127],"select":[130],"they":[132],"cannot":[133],"predict":[134],"agents'":[136],"beforehand.":[138],"employ":[140],"Q-learning":[142,158,238],"adjust":[145],"discount":[146],"rates":[147],"reliability":[150,160],"solve":[152,176],"above":[154],"mentioned":[155],"problems.":[156],"The":[157],"differentiate":[162],"into":[163,221],"preferring":[165,171],"give":[173],"problems":[179,205],"generated":[180],"functional":[186],"differentiation":[187],"addition,":[194],"we":[195,216],"try":[196],"decrease":[198],"generation":[200],"perceptual":[203,209],"aliasing":[204],"improving":[207],"ability":[210],"Through":[213],"experimental":[214],"results,":[215],"showed":[217],"differentiated":[220],"two":[222],"type":[223],"agents,":[225],"acquired":[227],"stable":[228],"avoidance":[230],"high":[233],"probability":[234],"than":[235],"conventional":[237]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}