{"id":"https://openalex.org/W3118726239","doi":"https://doi.org/10.1109/ssci47803.2020.9308290","title":"Coevolutionary Deep Reinforcement Learning","display_name":"Coevolutionary Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3118726239","doi":"https://doi.org/10.1109/ssci47803.2020.9308290","mag":"3118726239"},"language":"en","primary_location":{"id":"doi:10.1109/ssci47803.2020.9308290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci47803.2020.9308290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5006648643","display_name":"David Cotton","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Cotton","raw_affiliation_strings":["Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088037842","display_name":"Jason Traish","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jason Traish","raw_affiliation_strings":["Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016675373","display_name":"Zenon Chaczko","orcid":"https://orcid.org/0000-0002-2816-7510"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zenon Chaczko","raw_affiliation_strings":["Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1354,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59018208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2600","last_page":"2607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987000226974487,"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":0.9952999949455261,"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":0.8789223432540894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7644151449203491},{"id":"https://openalex.org/keywords/enabling","display_name":"Enabling","score":0.7047613859176636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6738929152488708},{"id":"https://openalex.org/keywords/coevolution","display_name":"Coevolution","score":0.5878849029541016},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5370610356330872},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.47450941801071167},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4597085118293762},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44962838292121887}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8789223432540894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644151449203491},{"id":"https://openalex.org/C22607594","wikidata":"https://www.wikidata.org/wiki/Q5375150","display_name":"Enabling","level":2,"score":0.7047613859176636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6738929152488708},{"id":"https://openalex.org/C33009525","wikidata":"https://www.wikidata.org/wiki/Q208841","display_name":"Coevolution","level":2,"score":0.5878849029541016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5370610356330872},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.47450941801071167},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4597085118293762},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44962838292121887},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci47803.2020.9308290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci47803.2020.9308290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W16011919","https://openalex.org/W44465109","https://openalex.org/W1533861849","https://openalex.org/W1597864774","https://openalex.org/W1714211023","https://openalex.org/W2049287437","https://openalex.org/W2100677568","https://openalex.org/W2107726111","https://openalex.org/W2111935653","https://openalex.org/W2112836703","https://openalex.org/W2121863487","https://openalex.org/W2129936995","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2151834591","https://openalex.org/W2155968351","https://openalex.org/W2161608691","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2296073425","https://openalex.org/W2301830273","https://openalex.org/W2596367596","https://openalex.org/W2724169821","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2762117857","https://openalex.org/W2766447205","https://openalex.org/W2770298516","https://openalex.org/W2787938642","https://openalex.org/W2913409451","https://openalex.org/W2949316697","https://openalex.org/W2951799221","https://openalex.org/W2963477884","https://openalex.org/W2964174623","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3041202696","https://openalex.org/W3103780890","https://openalex.org/W4214717370","https://openalex.org/W4288359891","https://openalex.org/W4297810554","https://openalex.org/W4298876402","https://openalex.org/W4394662461","https://openalex.org/W6601814988","https://openalex.org/W6631943919","https://openalex.org/W6637441126","https://openalex.org/W6676793763","https://openalex.org/W6679458411","https://openalex.org/W6683300800","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6735641298","https://openalex.org/W6740092555","https://openalex.org/W6744838376","https://openalex.org/W6745190604","https://openalex.org/W6748839928","https://openalex.org/W6758729514","https://openalex.org/W6761920647","https://openalex.org/W6772005887","https://openalex.org/W6863618527","https://openalex.org/W6947956204"],"related_works":["https://openalex.org/W3144412313","https://openalex.org/W2634235285","https://openalex.org/W1974860256","https://openalex.org/W2492504662","https://openalex.org/W2122994901","https://openalex.org/W4321381871","https://openalex.org/W200599908","https://openalex.org/W2151437643","https://openalex.org/W2020991882","https://openalex.org/W2386430105"],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,21,38,53,85,101,105],"learn":[3],"without":[4,26],"instruction":[5],"is":[6,36,49],"a":[7,54,67,110,126,136],"powerful":[8],"enabler":[9],"for":[10,15],"learning":[11,20,46,56,114],"systems.":[12],"A":[13],"mechanism":[14],"this,":[16],"selfplay,":[17],"allows":[18],"reinforcement":[19,113],"develop":[22],"high":[23],"performing":[24],"policies":[25],"large":[27],"datasets":[28],"or":[29],"expert":[30],"knowledge.":[31],"Despite":[32],"these":[33],"benefits,":[34],"self-play":[35,145],"known":[37],"be":[39,83],"less":[40,155],"sample":[41],"efficient":[42],"and":[43,65,103],"suffer":[44],"unstable":[45],"dynamics.":[47],"This":[48,88],"in":[50,96,130,157],"part":[51],"due":[52],"nonstationary":[55],"problem":[57],"where":[58],"an":[59,92],"agent's":[60],"actions":[61],"influence":[62],"their":[63],"opponents":[64],"as":[66],"consequence":[68],"the":[69,107,122,131,142],"training":[70,108,153],"data":[71],"they":[72],"receive.":[73],"In":[74],"this":[75],"paper":[76,89],"we":[77],"demonstrate":[78,117],"that":[79,118],"competitive":[80],"pressures":[81],"can":[82],"utilised":[84],"improve":[86],"self-play.":[87],"leverages":[90],"coevolution,":[91],"evolutionary":[93],"inspired":[94],"process":[95],"which":[97],"individuals":[98],"are":[99],"compelled":[100],"innovate":[102],"adapt,":[104],"optimise":[106],"of":[109,112,125],"population":[111],"agents.":[115],"We":[116],"our":[119,148],"algorithm":[120,149],"improves":[121],"final":[123],"performance":[124],"Rainbow":[127],"DQN":[128],"trained":[129],"game":[132],"Connect":[133],"Four,":[134],"achieving":[135],"15%":[137],"higher":[138],"win":[139],"percentage":[140],"over":[141],"next":[143],"leading":[144],"algorithm.":[146],"Furthermore,":[147],"exhibits":[150],"more":[151],"stable":[152],"with":[154],"variation":[156],"evaluation":[158],"performance.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}