{"id":"https://openalex.org/W2783268317","doi":"https://doi.org/10.1109/icmla.2017.0-184","title":"Learning to Coordinate with Deep Reinforcement Learning in Doubles Pong Game","display_name":"Learning to Coordinate with Deep Reinforcement Learning in Doubles Pong Game","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2783268317","doi":"https://doi.org/10.1109/icmla.2017.0-184","mag":"2783268317"},"language":"en","primary_location":{"id":"doi:10.1109/icmla.2017.0-184","doi":"https://doi.org/10.1109/icmla.2017.0-184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2017.0-184","pdf_url":null,"source":{"id":"https://openalex.org/S4363607906","display_name":"IEEE International Conference on Machine Learning and Applications (ICMLA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5014594519","display_name":"Elhadji Amadou Oury Diallo","orcid":"https://orcid.org/0000-0001-6441-7719","observed_orcids":["https://orcid.org/0000-0001-6441-7719"]},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Elhadji Amadou Oury Diallo","raw_affiliation_strings":["Waseda Daigaku, Shinjuku-ku, Tokyo, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda Daigaku, Shinjuku-ku, Tokyo, JP","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035398314","display_name":"Ayumi Sugiyama","orcid":"https://orcid.org/0000-0002-2377-8603","observed_orcids":["https://orcid.org/0000-0002-2377-8603"]},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ayumi Sugiyama","raw_affiliation_strings":["Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082205147","display_name":"Toshiharu Sugawara","orcid":"https://orcid.org/0000-0002-9271-4507","observed_orcids":["https://orcid.org/0000-0002-9271-4507"]},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshiharu Sugawara","raw_affiliation_strings":["Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.6235,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.72812011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"14","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0003000000142492354,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":9.999999747378752e-05,"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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.7129999995231628},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.7480000257492065},{"id":"https://openalex.org/keywords/cooperative-behavior","display_name":"cooperative behavior","score":0.8999999761581421},{"id":"https://openalex.org/keywords/reward-systems","display_name":"reward systems","score":0.828000009059906},{"id":"https://openalex.org/keywords/sequential-decision-making","display_name":"sequential decision making","score":0.5709999799728394},{"id":"https://openalex.org/keywords/game-agents","display_name":"game-playing agents","score":0.4390000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946071624755859},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7856118679046631},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6609392166137695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5056247711181641},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.43501579761505127},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.381536602973938},{"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":[{"id":"doi:10.1109/icmla.2017.0-184","doi":"https://doi.org/10.1109/icmla.2017.0-184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2017.0-184","pdf_url":null,"source":{"id":"https://openalex.org/S4363607906","display_name":"IEEE International Conference on Machine Learning and Applications (ICMLA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4757044010","display_name":"Improving sustainability, flexibility, and robustness of artifactitious systems using emergence of divisional cooperation","funder_award_id":"17KT0044","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W142858861","https://openalex.org/W1496590343","https://openalex.org/W1522301498","https://openalex.org/W1541793934","https://openalex.org/W1565538015","https://openalex.org/W1757796397","https://openalex.org/W2007973245","https://openalex.org/W2049975267","https://openalex.org/W2104602264","https://openalex.org/W2121863487","https://openalex.org/W2136398072","https://openalex.org/W2145339207","https://openalex.org/W2147492008","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2172933221","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2475089067","https://openalex.org/W2489822048","https://openalex.org/W2508066198","https://openalex.org/W2575731723","https://openalex.org/W2592798481","https://openalex.org/W2594794854","https://openalex.org/W2597433764","https://openalex.org/W2604283518","https://openalex.org/W2604873668","https://openalex.org/W2746553466","https://openalex.org/W2951896791","https://openalex.org/W2962941327","https://openalex.org/W2964121744","https://openalex.org/W2964191473","https://openalex.org/W3011120880","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W2620865396","https://openalex.org/W2414054180"],"abstract_inverted_index":{"This":[0],"paper":[1],"discusses":[2],"the":[3,34,45,60,71,220],"emergence":[4],"of":[5,26,33,38,59,149,189],"cooperative":[6,67,115,184],"and":[7,12,47,62,78,93,125,151,176,202,210],"coordinated":[8],"behaviors":[9,185],"between":[10],"joint":[11,222],"concurrent":[13],"learning":[14,177],"agents":[15,81,108,142,200],"using":[16,109],"deep":[17,110],"Q-learning.":[18],"Multi-agent":[19],"systems":[20,41],"(MAS)":[21],"arise":[22],"in":[23,44,207],"a":[24,84],"variety":[25],"domains.":[27],"The":[28],"collective":[29],"effort":[30],"is":[31,57,96],"one":[32,58],"main":[35],"building":[36],"blocks":[37],"many":[39],"fundamental":[40],"that":[42,182,219],"exist":[43],"world,":[46],"thus,":[48],"sequential":[49],"decision":[50],"making":[51],"under":[52],"uncertainty":[53],"for":[54,65,73],"collaborative":[55],"work":[56],"important":[61],"challenging":[63],"issues":[64],"intelligent":[66],"multiple":[68],"agents.":[69],"However,":[70],"decisions":[72],"cooperation":[74],"are":[75,224],"highly":[76],"sophisticated":[77],"complicated":[79],"because":[80],"may":[82],"have":[83],"certain":[85],"shared":[86],"goal":[87],"or":[88],"individual":[89,216],"goals":[90],"to":[91,105,131,145,158,170,196],"achieve":[92],"their":[94,133,147,215],"behavior":[95,167],"inevitably":[97],"influenced":[98],"by":[99],"each":[100,152,205],"other.":[101],"Therefore,":[102],"we":[103,126],"attempt":[104],"explore":[106],"whether":[107],"Q-networks":[111],"(DQN)":[112],"can":[113],"learn":[114,130,144],"behavior.":[116,161],"We":[117,162],"use":[118],"doubles":[119],"pong":[120],"game":[121,137],"as":[122],"an":[123],"example":[124],"investigate":[127,164],"how":[128,165,199,211],"they":[129,212],"divide":[132,146],"works":[134],"through":[135],"iterated":[136],"executions.":[138],"In":[139],"our":[140],"approach,":[141],"jointly":[143],"area":[148],"responsibility":[150],"agent":[153],"uses":[154],"its":[155,160],"own":[156],"DQN":[157],"modify":[159],"also":[163],"learned":[166],"changes":[168],"according":[169],"environmental":[171],"characteristics":[172],"including":[173],"reward":[174],"schemes":[175],"techniques.":[178],"Our":[179],"experiments":[180],"indicate":[181],"effective":[183],"with":[186,204],"balanced":[187],"division":[188],"workload":[190],"emerge.":[191],"These":[192],"results":[193],"help":[194],"us":[195],"better":[197],"understand":[198],"behave":[201],"interact":[203],"other":[206],"complex":[208],"environments":[209],"coherently":[213],"choose":[214],"actions":[217,223],"such":[218],"resulting":[221],"optimal.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}