{"id":"https://openalex.org/W2963373847","doi":"https://doi.org/10.1162/isal_a_00148","title":"Reinforcement Learning Agents acquire Flocking and Symbiotic Behaviour in Simulated Ecosystems","display_name":"Reinforcement Learning Agents acquire Flocking and Symbiotic Behaviour in Simulated Ecosystems","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2963373847","doi":"https://doi.org/10.1162/isal_a_00148","mag":"2963373847"},"language":"en","primary_location":{"id":"doi:10.1162/isal_a_00148","is_oa":true,"landing_page_url":"https://doi.org/10.1162/isal_a_00148","pdf_url":"https://direct.mit.edu/isal/proceedings-pdf/isal2019/31/103/1903575/isal_a_00148.pdf","source":{"id":"https://openalex.org/S4363608301","display_name":"The 2019 Conference on Artificial Life","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"The 2019 Conference on Artificial Life","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://direct.mit.edu/isal/proceedings-pdf/isal2019/31/103/1903575/isal_a_00148.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046100176","display_name":"Peter Sunehag","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Peter Sunehag","raw_affiliation_strings":["DeepMind, London UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031943811","display_name":"Guy Lever","orcid":"https://orcid.org/0000-0001-9551-1839"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guy Lever","raw_affiliation_strings":["DeepMind, London UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390229","display_name":"Siqi Liu","orcid":"https://orcid.org/0000-0002-0605-2958"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Siqi Liu","raw_affiliation_strings":["DeepMind, London UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080814522","display_name":"Josh Merel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josh Merel","raw_affiliation_strings":["DeepMind, London UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062951341","display_name":"Nicolas Heess","orcid":"https://orcid.org/0000-0001-7876-9256"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nicolas Heess","raw_affiliation_strings":["DeepMind, London UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054808675","display_name":"Joel Z. Leibo","orcid":"https://orcid.org/0000-0002-3153-916X"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joel Z. Leibo","raw_affiliation_strings":["DeepMind, London UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006947993","display_name":"Edward Hughes","orcid":"https://orcid.org/0000-0002-2434-2334"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Edward Hughes","raw_affiliation_strings":["DeepMind, London UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019669511","display_name":"Tom Eccles","orcid":"https://orcid.org/0000-0001-6706-017X"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tom Eccles","raw_affiliation_strings":["DeepMind, London UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051619646","display_name":"Thore Graepel","orcid":"https://orcid.org/0000-0003-3957-0310"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thore Graepel","raw_affiliation_strings":["DeepMind, London UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London UK","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5046100176"],"corresponding_institution_ids":["https://openalex.org/I4210090411"],"apc_list":null,"apc_paid":null,"fwci":5.448,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.96032609,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9980999827384949,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9868999719619751,"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/T11764","display_name":"Evolution and Genetic Dynamics","score":0.9837999939918518,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/flocking","display_name":"Flocking (texture)","score":0.9165506362915039},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.803577184677124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5987434387207031},{"id":"https://openalex.org/keywords/ecosystem","display_name":"Ecosystem","score":0.5385398268699646},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5000505447387695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4157561659812927},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.20368990302085876},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1818762719631195},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07682088017463684},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06266254186630249}],"concepts":[{"id":"https://openalex.org/C2781220375","wikidata":"https://www.wikidata.org/wiki/Q814208","display_name":"Flocking (texture)","level":2,"score":0.9165506362915039},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.803577184677124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5987434387207031},{"id":"https://openalex.org/C110872660","wikidata":"https://www.wikidata.org/wiki/Q37813","display_name":"Ecosystem","level":2,"score":0.5385398268699646},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5000505447387695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4157561659812927},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.20368990302085876},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1818762719631195},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07682088017463684},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06266254186630249},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/isal_a_00148","is_oa":true,"landing_page_url":"https://doi.org/10.1162/isal_a_00148","pdf_url":"https://direct.mit.edu/isal/proceedings-pdf/isal2019/31/103/1903575/isal_a_00148.pdf","source":{"id":"https://openalex.org/S4363608301","display_name":"The 2019 Conference on Artificial Life","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"The 2019 Conference on Artificial Life","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10090817","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10090817/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In: Fellermann, H and Bacardit, J and GoniMoreno, A and Fuchslin, R, (eds.) Proceedings of the Artificial Life Conference.  (pp. pp. 103-110).  MIT Press (2019)     ","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"doi:10.1162/isal_a_00148","is_oa":true,"landing_page_url":"https://doi.org/10.1162/isal_a_00148","pdf_url":"https://direct.mit.edu/isal/proceedings-pdf/isal2019/31/103/1903575/isal_a_00148.pdf","source":{"id":"https://openalex.org/S4363608301","display_name":"The 2019 Conference on Artificial Life","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"The 2019 Conference on Artificial Life","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963373847.pdf","grobid_xml":"https://content.openalex.org/works/W2963373847.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W634197672","https://openalex.org/W1481650321","https://openalex.org/W1492640216","https://openalex.org/W1542941925","https://openalex.org/W1967771982","https://openalex.org/W1974824132","https://openalex.org/W2003251517","https://openalex.org/W2004827430","https://openalex.org/W2005946215","https://openalex.org/W2018091400","https://openalex.org/W2064675550","https://openalex.org/W2078148033","https://openalex.org/W2097209337","https://openalex.org/W2102080017","https://openalex.org/W2121863487","https://openalex.org/W2158782408","https://openalex.org/W2312562567","https://openalex.org/W2588790649","https://openalex.org/W2726187156","https://openalex.org/W2785738552","https://openalex.org/W2786036274","https://openalex.org/W2963407617","https://openalex.org/W2964345382"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4309344700","https://openalex.org/W4206669594","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W4296549211","https://openalex.org/W4285119242","https://openalex.org/W260766989","https://openalex.org/W3203437449","https://openalex.org/W3139193008"],"abstract_inverted_index":{"In":[0,61],"nature,":[1],"group":[2,266],"behaviours":[3],"such":[4,24],"as":[5,7,9,88,139,141],"flocking":[6],"well":[8,140],"cross-species":[10],"symbiotic":[11],"partnerships":[12],"are":[13,213],"observed":[14,229],"in":[15,28,34,57,142,176,198,203,237,244,272,308],"vastly":[16],"different":[17,129,192,200],"forms":[18,47,97],"and":[19,41,122,157,163,172,222,257,263,268,279,292,330],"circumstances.":[20],"We":[21,43,124,313],"hypothesize":[22],"that":[23,75,212,223,301],"strategies":[25],"can":[26,50],"arise":[27],"response":[29],"to":[30,63,149,215,319,323,328],"generic":[31,111],"predator-prey":[32],"pressures":[33],"a":[35,89,110,131,143,290,315,338],"spatial":[36],"environment":[37],"with":[38,135,147],"range-limited":[39],"sensation":[40],"action.":[42],"evaluate":[44],"whether":[45,85],"these":[46,95,168],"of":[48,91,98,109,137,188,195,228,235,299,334,340],"coordination":[49,79,86,160],"emerge":[51],"by":[52,305],"independent":[53,189],"multi-agent":[54],"reinforcement":[55,178,269,282],"learning":[56,179,270,283],"simple":[58,341],"multiple-species":[59],"ecosystems.":[60],"contrast":[62],"prior":[64],"work,":[65],"we":[66,83,170,331],"avoid":[67],"hand-crafted":[68],"shaping":[69],"rewards,":[70],"specific":[71,96],"actions,":[72],"or":[73,260],"dynamics":[74],"would":[76],"directly":[77],"encourage":[78],"across":[80,164,225],"agents.":[81,231],"Instead":[82],"test":[84],"emerges":[87],"consequence":[90],"adaptation":[92],"without":[93],"encouraging":[94],"coordination,":[99],"which":[100],"only":[101],"has":[102,251],"indirect":[103],"benefit.":[104],"Our":[105],"simulated":[106],"ecosystems":[107,239],"consist":[108],"food":[112],"chain":[113],"involving":[114],"three":[115],"trophic":[116],"levels:":[117],"apex":[118],"predator,":[119,121],"mid-level":[120],"prey.":[123],"conduct":[125],"experiments":[126],"on":[127,254,265],"two":[128],"platforms,":[130],"3D":[132],"physics":[133],"engine":[134],"tens":[136],"agents":[138,190],"2D":[144],"grid":[145],"world":[146],"up":[148],"thousands.":[150],"The":[151,206],"results":[152],"clearly":[153],"confirm":[154],"our":[155],"hypothesis":[156],"show":[158],"substantial":[159],"both":[161],"within":[162,180],"species.":[165],"To":[166],"obtain":[167],"results,":[169],"leverage":[171],"adapt":[173],"recent":[174],"advances":[175],"deep":[177],"an":[181],"ecosystem":[182],"training":[183],"protocol":[184],"featuring":[185],"homogeneous":[186],"groups":[187],"from":[191,317,337],"species":[193],"(sets":[194],"policies),":[196],"acting":[197],"many":[199],"random":[201],"combinations":[202],"parallel":[204],"habitats.":[205],"policies":[207],"utilize":[208,314],"neural":[209],"network":[210],"architectures":[211],"invariant":[214],"agent":[216],"individuality":[217],"but":[218],"not":[219],"type":[220],"(species)":[221],"generalize":[224],"varying":[226],"numbers":[227],"other":[230],"While":[232],"the":[233,245,249,277,296,309],"emergence":[234,333],"complexity":[236,256,267],"artificial":[238,246,310],"have":[240],"long":[241],"been":[242,252],"studied":[243],"life":[247,311],"community,":[248],"focus":[250],"more":[253],"individual":[255],"genetic":[258,306],"algorithms":[259,307],"explicit":[261],"modelling,":[262],"less":[264],"emphasized":[271],"this":[273],"article.":[274],"Unlike":[275],"what":[276],"name":[278],"intuition":[280],"suggests,":[281],"adapts":[284],"over":[285],"evolutionary":[286],"history":[287],"rather":[288],"than":[289],"life-time":[291],"is":[293,302],"here":[294],"addressing":[295],"sequential":[297],"optimization":[298,342],"fitness":[300],"usually":[303],"approached":[304],"community.":[312],"shift":[316],"procedures":[318],"objectives,":[320],"allowing":[321],"us":[322],"bring":[324],"new":[325],"powerful":[326],"machinery":[327],"bare,":[329],"see":[332],"complex":[335],"behaviour":[336],"sequence":[339],"problems.":[343]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}