{"id":"https://openalex.org/W2809097245","doi":"https://doi.org/10.1162/evco_a_00232","title":"Emergent Solutions to High-Dimensional Multitask Reinforcement Learning","display_name":"Emergent Solutions to High-Dimensional Multitask Reinforcement Learning","publication_year":2018,"publication_date":"2018-06-22","ids":{"openalex":"https://openalex.org/W2809097245","doi":"https://doi.org/10.1162/evco_a_00232","mag":"2809097245","pmid":"https://pubmed.ncbi.nlm.nih.gov/29932363"},"language":"en","primary_location":{"id":"doi:10.1162/evco_a_00232","is_oa":true,"landing_page_url":"https://doi.org/10.1162/evco_a_00232","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/evco_a_00232","source":{"id":"https://openalex.org/S38677346","display_name":"Evolutionary Computation","issn_l":"1063-6560","issn":["1063-6560","1530-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Evolutionary Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/evco_a_00232","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101949050","display_name":"Stephen Kelly","orcid":"https://orcid.org/0000-0002-6071-4705"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Stephen Kelly","raw_affiliation_strings":["Department of Computer Science, Dalhousie University, 6050 University Avenue, Halifax, NS, B3H 4R2, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Dalhousie University, 6050 University Avenue, Halifax, NS, B3H 4R2, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003699164","display_name":"Malcolm I. Heywood","orcid":"https://orcid.org/0000-0002-1521-0671"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Malcolm I. Heywood","raw_affiliation_strings":["Department of Computer Science, Dalhousie University, 6050 University Avenue, Halifax, NS, B3H 4R2, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Dalhousie University, 6050 University Avenue, Halifax, NS, B3H 4R2, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003699164","https://openalex.org/A5101949050"],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":null,"apc_paid":null,"fwci":3.554,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94223028,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"26","issue":"3","first_page":"347","last_page":"380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9991000294685364,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9991000294685364,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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":0.9962000250816345,"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":0.9210875630378723},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8053169250488281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6502044200897217},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6090070009231567},{"id":"https://openalex.org/keywords/neuroevolution","display_name":"Neuroevolution","score":0.5388566851615906},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5234705209732056},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5075046420097351},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.447061151266098},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4398949146270752},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41219785809516907}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9210875630378723},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8053169250488281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6502044200897217},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6090070009231567},{"id":"https://openalex.org/C118070581","wikidata":"https://www.wikidata.org/wiki/Q2060528","display_name":"Neuroevolution","level":3,"score":0.5388566851615906},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5234705209732056},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5075046420097351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.447061151266098},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4398949146270752},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41219785809516907},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003299","descriptor_name":"Cooperative Behavior","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003299","descriptor_name":"Cooperative Behavior","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003299","descriptor_name":"Cooperative Behavior","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005716","descriptor_name":"Game Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005716","descriptor_name":"Game Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005716","descriptor_name":"Game Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1162/evco_a_00232","is_oa":true,"landing_page_url":"https://doi.org/10.1162/evco_a_00232","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/evco_a_00232","source":{"id":"https://openalex.org/S38677346","display_name":"Evolutionary Computation","issn_l":"1063-6560","issn":["1063-6560","1530-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Evolutionary Computation","raw_type":"journal-article"},{"id":"pmid:29932363","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29932363","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Evolutionary computation","raw_type":null}],"best_oa_location":{"id":"doi:10.1162/evco_a_00232","is_oa":true,"landing_page_url":"https://doi.org/10.1162/evco_a_00232","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/evco_a_00232","source":{"id":"https://openalex.org/S38677346","display_name":"Evolutionary Computation","issn_l":"1063-6560","issn":["1063-6560","1530-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Evolutionary Computation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2809097245.pdf","grobid_xml":"https://content.openalex.org/works/W2809097245.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W113028485","https://openalex.org/W608314793","https://openalex.org/W1506853907","https://openalex.org/W1512866498","https://openalex.org/W1565746575","https://openalex.org/W1583742283","https://openalex.org/W1593492645","https://openalex.org/W1658008008","https://openalex.org/W1985849007","https://openalex.org/W1998452541","https://openalex.org/W2055239208","https://openalex.org/W2082953382","https://openalex.org/W2098879935","https://openalex.org/W2099397840","https://openalex.org/W2100506021","https://openalex.org/W2100844966","https://openalex.org/W2103476564","https://openalex.org/W2105802878","https://openalex.org/W2130774030","https://openalex.org/W2145339207","https://openalex.org/W2151083897","https://openalex.org/W2153357128","https://openalex.org/W2155968351","https://openalex.org/W2163467402","https://openalex.org/W2174786457","https://openalex.org/W2190606234","https://openalex.org/W2191710555","https://openalex.org/W2253367123","https://openalex.org/W2272482229","https://openalex.org/W2604908377","https://openalex.org/W2724228633","https://openalex.org/W2791039059","https://openalex.org/W2914461813","https://openalex.org/W2914584698","https://openalex.org/W2915198056","https://openalex.org/W2949819354","https://openalex.org/W2964043796","https://openalex.org/W3103780890","https://openalex.org/W4211089519","https://openalex.org/W4245055982","https://openalex.org/W4252634232","https://openalex.org/W4292936315"],"related_works":["https://openalex.org/W2168909409","https://openalex.org/W2144357723","https://openalex.org/W2950402165","https://openalex.org/W2114981325","https://openalex.org/W4302038648","https://openalex.org/W2099397840","https://openalex.org/W2249125133","https://openalex.org/W2811365478","https://openalex.org/W2735321217","https://openalex.org/W2962258836"],"abstract_inverted_index":{"Algorithms":[0],"that":[1,112],"learn":[2],"through":[3,45,73],"environmental":[4],"interaction":[5,74],"and":[6,22,55],"delayed":[7],"rewards,":[8],"or":[9],"reinforcement":[10,86,101],"learning":[11,87,102,121],"(RL),":[12],"increasingly":[13],"face":[14],"the":[15,43,51,76,90,113,117,143,154,192],"challenge":[16],"of":[17,119,126,129,142,158,186],"scaling":[18],"to":[19,31,38,134,149,161],"dynamic,":[20],"high-dimensional,":[21],"partially":[23],"observable":[24],"environments.":[25],"Significant":[26],"attention":[27],"is":[28,53,156],"being":[29,123],"paid":[30],"frameworks":[32,88,103],"from":[33,191],"deep":[34,85,120],"learning,":[35],"which":[36,69],"scale":[37],"high-dimensional":[39],"data":[40],"by":[41],"decomposing":[42],"task":[44],"multilayered":[46],"neural":[47],"networks.":[48],"While":[49],"effective,":[50],"representation":[52],"complex":[54],"computationally":[56],"demanding.":[57],"In":[58,171],"this":[59,172],"work,":[60],"we":[61],"propose":[62],"a":[63,80,106,124],"framework":[64],"based":[65,104],"on":[66,105],"genetic":[67],"programming":[68],"adaptively":[70],"complexifies":[71],"policies":[72],"with":[75,83,132,166],"task.":[77],"We":[78],"make":[79],"direct":[81],"comparison":[82],"several":[84],"in":[89,139],"challenging":[91],"Atari":[92],"video":[93],"game":[94,163,179],"environment":[95],"as":[96,98,180,182],"well":[97,181],"more":[99],"traditional":[100],"priori":[107],"engineered":[108],"features.":[109],"Results":[110],"indicate":[111],"proposed":[114],"approach":[115,155],"matches":[116],"quality":[118],"while":[122],"minimum":[125],"three":[127],"orders":[128],"magnitude":[130],"simpler":[131],"respect":[133],"model":[135],"complexity.":[136],"This":[137],"results":[138],"real-time":[140],"operation":[141],"champion":[144],"RL":[145],"agent":[146,174],"without":[147],"recourse":[148],"specialized":[150],"hardware":[151],"support.":[152],"Moreover,":[153],"capable":[157,185],"evolving":[159],"solutions":[160],"multiple":[162],"titles":[164],"simultaneously":[165],"no":[167],"additional":[168],"computational":[169],"cost.":[170],"case,":[173],"behaviours":[175],"for":[176],"an":[177],"individual":[178],"single":[183],"agents":[184],"playing":[187],"all":[188],"games":[189],"emerge":[190],"same":[193],"evolutionary":[194],"run.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}