{"id":"https://openalex.org/W3091416427","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207657","title":"Multi-Agent Pattern Formation: a Distributed Model-Free Deep Reinforcement Learning Approach","display_name":"Multi-Agent Pattern Formation: a Distributed Model-Free Deep Reinforcement Learning Approach","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3091416427","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207657","mag":"3091416427"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5014594519","display_name":"Elhadji Amadou Oury Diallo","orcid":"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":true,"raw_author_name":"Elhadji Amadou Oury Diallo","raw_affiliation_strings":["Computer Science and Communications Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"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"},"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":["Computer Science and Communications Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Computer Science and Communications Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014594519"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":1.0605,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82331257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9833999872207642,"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":0.8507747650146484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8372286558151245},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5923269391059875},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5886967778205872},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5697030425071716},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5365512371063232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4950360357761383},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4348198473453522},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4316380023956299}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8507747650146484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8372286558151245},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5923269391059875},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5886967778205872},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5697030425071716},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5365512371063232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4950360357761383},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4348198473453522},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4316380023956299},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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":42,"referenced_works":["https://openalex.org/W55330286","https://openalex.org/W1757796397","https://openalex.org/W1946137962","https://openalex.org/W1994237189","https://openalex.org/W2014192044","https://openalex.org/W2044484214","https://openalex.org/W2060447811","https://openalex.org/W2088956500","https://openalex.org/W2106683849","https://openalex.org/W2108096938","https://openalex.org/W2142924305","https://openalex.org/W2145339207","https://openalex.org/W2165744313","https://openalex.org/W2166967570","https://openalex.org/W2173248099","https://openalex.org/W2224943858","https://openalex.org/W2498529546","https://openalex.org/W2768629321","https://openalex.org/W2807741983","https://openalex.org/W2883532348","https://openalex.org/W2963864421","https://openalex.org/W2963934958","https://openalex.org/W3006080536","https://openalex.org/W3011120880","https://openalex.org/W3038022425","https://openalex.org/W3182098362","https://openalex.org/W3182674124","https://openalex.org/W3209101326","https://openalex.org/W4288351558","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W6602261655","https://openalex.org/W6637967152","https://openalex.org/W6684562998","https://openalex.org/W6684921986","https://openalex.org/W6689473553","https://openalex.org/W6738796088","https://openalex.org/W6746513637","https://openalex.org/W6752380930","https://openalex.org/W6763464472","https://openalex.org/W6773745691","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"investigate":[4],"how":[5,55],"a":[6,27,41,71],"large-scale":[7,119],"system":[8],"of":[9,43,87,96,133,137,140,142],"independently":[10,136],"learning":[11,32,93],"agents":[12,47,104],"can":[13,111],"collectively":[14,61],"form":[15,62],"acceptable":[16],"two-dimensional":[17],"patterns":[18,108],"(pattern":[19],"formation)":[20],"from":[21],"any":[22],"initial":[23],"configuration.":[24],"We":[25,100],"propose":[26],"decentralized":[28],"multi-agent":[29],"deep":[30],"reinforcement":[31],"architecture":[33],"MAPF-DQN":[34,110],"(Multi-Agent":[35],"Pattern":[36],"Formation":[37],"DQN)":[38],"in":[39,118],"which":[40],"set":[42],"independent":[44],"and":[45,53,75,83],"distributed":[46],"capture":[48],"their":[49,67],"local":[50],"visual":[51],"field":[52],"learn":[54],"to":[56,60,81],"act":[57],"so":[58],"as":[59,90,92],"target":[63,76],"shapes.":[64],"Agents":[65],"exploit":[66],"individual":[68],"networks":[69,77],"with":[70],"central":[72],"replay":[73],"memory":[74],"that":[78,103,124],"are":[79],"used":[80],"store":[82],"update":[84],"the":[85,88,94,97,125,134,138],"representation":[86],"environment":[89],"well":[91],"dynamics":[95],"other":[98],"agents.":[99,143],"then":[101],"show":[102],"trained":[105],"on":[106,131],"random":[107],"using":[109],"organize":[112],"themselves":[113],"into":[114],"very":[115],"complex":[116],"shapes":[117],"environments.":[120],"Our":[121],"results":[122],"suggest":[123],"proposed":[126],"framework":[127],"achieves":[128],"zero-shot":[129],"generalization":[130],"most":[132],"environments":[135],"depth":[139],"view":[141]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}