{"id":"https://openalex.org/W4221012070","doi":"https://doi.org/10.1007/s10458-022-09548-8","title":"Quantifying the effects of environment and population diversity in multi-agent reinforcement learning","display_name":"Quantifying the effects of environment and population diversity in multi-agent reinforcement learning","publication_year":2022,"publication_date":"2022-03-18","ids":{"openalex":"https://openalex.org/W4221012070","doi":"https://doi.org/10.1007/s10458-022-09548-8"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-022-09548-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-022-09548-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-022-09548-8.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10458-022-09548-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013841168","display_name":"Kevin R. McKee","orcid":"https://orcid.org/0000-0002-4412-1686"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google 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":"Kevin R. McKee","raw_affiliation_strings":["DeepMind Technologies Ltd, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-4412-1686","affiliations":[{"raw_affiliation_string":"DeepMind Technologies Ltd, London, United Kingdom","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":"Google 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 Technologies Ltd, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies Ltd, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002746172","display_name":"Charlie Beattie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google 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":"Charlie Beattie","raw_affiliation_strings":["DeepMind Technologies Ltd, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies Ltd, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007090604","display_name":"Richard Everett","orcid":"https://orcid.org/0000-0002-9404-6338"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google 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":"Richard Everett","raw_affiliation_strings":["DeepMind Technologies Ltd, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies Ltd, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013841168"],"corresponding_institution_ids":["https://openalex.org/I4210090411"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":2.2197,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89282951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"36","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9955000281333923,"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.8361619710922241},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.7542864680290222},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7350315451622009},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.6369165182113647},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6247222423553467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.614540159702301},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5901274681091309},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4399207532405853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4008313715457916},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3315943479537964},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.32852819561958313},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2376699149608612},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.14885708689689636},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13948315382003784},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11360591650009155}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8361619710922241},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.7542864680290222},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7350315451622009},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.6369165182113647},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6247222423553467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614540159702301},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5901274681091309},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4399207532405853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4008313715457916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3315943479537964},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32852819561958313},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2376699149608612},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.14885708689689636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13948315382003784},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11360591650009155},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10458-022-09548-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-022-09548-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-022-09548-8.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2102.08370","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.08370","pdf_url":"https://arxiv.org/pdf/2102.08370","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/s10458-022-09548-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-022-09548-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-022-09548-8.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221012070.pdf","grobid_xml":"https://content.openalex.org/works/W4221012070.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1572054464","https://openalex.org/W1597864774","https://openalex.org/W2018803503","https://openalex.org/W2027473728","https://openalex.org/W2109910161","https://openalex.org/W2113723352","https://openalex.org/W2121044470","https://openalex.org/W2139612737","https://openalex.org/W2318802957","https://openalex.org/W2594103415","https://openalex.org/W2623431351","https://openalex.org/W2739364177","https://openalex.org/W2750605955","https://openalex.org/W2788741142","https://openalex.org/W2810602713","https://openalex.org/W2891076394","https://openalex.org/W2891661335","https://openalex.org/W2895921264","https://openalex.org/W2903181768","https://openalex.org/W2945199479","https://openalex.org/W2954700257","https://openalex.org/W2959402823","https://openalex.org/W2966556569","https://openalex.org/W2970894611","https://openalex.org/W2982316857","https://openalex.org/W3004902652","https://openalex.org/W3040507763","https://openalex.org/W3099518626","https://openalex.org/W3100851130","https://openalex.org/W3186028890","https://openalex.org/W3211037481","https://openalex.org/W4212774754","https://openalex.org/W4298516805","https://openalex.org/W6631984995","https://openalex.org/W6635751388","https://openalex.org/W6695962426","https://openalex.org/W6757444583","https://openalex.org/W6758729514","https://openalex.org/W6775695405"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2076061571","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2501594388"],"abstract_inverted_index":{"Abstract":[0],"Generalization":[1],"is":[2],"a":[3,76,89,117],"major":[4],"challenge":[5],"for":[6],"multi-agent":[7,42,48],"reinforcement":[8],"learning.":[9],"How":[10],"well":[11],"does":[12],"an":[13],"agent":[14,58,64,123],"perform":[15],"when":[16],"placed":[17],"in":[18,22,40,71,125],"novel":[19],"environments":[20,49],"and":[21,32,38,101],"interactions":[23],"with":[24,116],"new":[25,90],"co-players?":[26],"In":[27,113],"this":[28],"paper,":[29],"we":[30],"investigate":[31],"quantify":[33],"the":[34,41,45,67,81],"relationship":[35],"between":[36],"generalization":[37],"diversity":[39],"domain.":[43],"Across":[44],"range":[46],"of":[47,83,93,108,120],"considered":[50],"here,":[51],"procedurally":[52],"generating":[53,109],"training":[54,72,115],"levels":[55,69],"significantly":[56],"improves":[57],"performance":[59,65,124],"on":[60,66],"held-out":[61],"levels.":[62],"However,":[63],"specific":[68],"used":[70],"sometimes":[73],"declines":[74],"as":[75],"result.":[77],"To":[78],"better":[79],"understand":[80],"effects":[82],"co-player":[84],"variation,":[85],"our":[86],"experiments":[87],"introduce":[88],"environment-agnostic":[91],"measure":[92],"behavioral":[94],"diversity.":[95,112],"Results":[96],"demonstrate":[97],"that":[98],"population":[99,111],"size":[100],"intrinsic":[102],"motivation":[103],"are":[104],"both":[105],"effective":[106],"methods":[107],"greater":[110],"turn,":[114],"diverse":[118],"set":[119],"co-players":[121],"strengthens":[122],"some":[126],"(but":[127],"not":[128],"all)":[129],"cases.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}