{"id":"https://openalex.org/W2891076394","doi":"https://doi.org/10.1609/aaai.v33i01.33013796","title":"Multi-Task Deep Reinforcement Learning with PopArt","display_name":"Multi-Task Deep Reinforcement Learning with PopArt","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2891076394","doi":"https://doi.org/10.1609/aaai.v33i01.33013796","mag":"2891076394"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33013796","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013796","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33013796","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036908874","display_name":"Matteo Hessel","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":"Matteo Hessel","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046090328","display_name":"Hubert Soyer","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":"Hubert Soyer","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011235627","display_name":"Lasse Espeholt","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":"Lasse Espeholt","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064372346","display_name":"Wojciech Marian Czarnecki","orcid":"https://orcid.org/0000-0002-2641-9542"},"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":"Wojciech Czarnecki","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059285443","display_name":"Simon Schmitt","orcid":"https://orcid.org/0000-0001-6219-2130"},"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":"Simon Schmitt","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033135596","display_name":"Hado van Hasselt","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":"Hado Van Hasselt","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090411"],"apc_list":null,"apc_paid":null,"fwci":14.4333,"has_fulltext":true,"cited_by_count":205,"citation_normalized_percentile":{"value":0.99193386,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"33","issue":"01","first_page":"3796","last_page":"3803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9728999733924866,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9375,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8186380863189697},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.7900636196136475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7847579717636108},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7354748845100403},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5979142189025879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5951957106590271},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5660930275917053},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5636303424835205},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4971466362476349},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4718128442764282},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44485703110694885},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4145185351371765},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07462704181671143}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8186380863189697},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.7900636196136475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7847579717636108},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7354748845100403},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5979142189025879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5951957106590271},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5660930275917053},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5636303424835205},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4971466362476349},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4718128442764282},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44485703110694885},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4145185351371765},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07462704181671143},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33013796","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013796","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4266","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4266","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4266/4144","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33013796","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013796","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W1513681384","https://openalex.org/W1514587017","https://openalex.org/W1517383877","https://openalex.org/W1520871589","https://openalex.org/W1658008008","https://openalex.org/W1682403713","https://openalex.org/W1771410628","https://openalex.org/W2031727428","https://openalex.org/W2047057213","https://openalex.org/W2060277733","https://openalex.org/W2076337359","https://openalex.org/W2084920657","https://openalex.org/W2101493843","https://openalex.org/W2103220021","https://openalex.org/W2116386744","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2132622533","https://openalex.org/W2133013156","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2161905760","https://openalex.org/W2173248099","https://openalex.org/W2174786457","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2280163991","https://openalex.org/W2342662072","https://openalex.org/W2509374375","https://openalex.org/W2522489477","https://openalex.org/W2549401308","https://openalex.org/W2550821151","https://openalex.org/W2551887912","https://openalex.org/W2556468274","https://openalex.org/W2560647685","https://openalex.org/W2563830277","https://openalex.org/W2593765977","https://openalex.org/W2601066903","https://openalex.org/W2612610049","https://openalex.org/W2735995851","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2772709170","https://openalex.org/W2786036274","https://openalex.org/W2788146012","https://openalex.org/W2800877957","https://openalex.org/W2950872548","https://openalex.org/W2952509347","https://openalex.org/W2963009616","https://openalex.org/W2963211300","https://openalex.org/W2963864421","https://openalex.org/W2963877604","https://openalex.org/W2964043796","https://openalex.org/W2964227312","https://openalex.org/W3011120880","https://openalex.org/W3103780890","https://openalex.org/W4230563027","https://openalex.org/W4239187508","https://openalex.org/W4297795161","https://openalex.org/W4297797010","https://openalex.org/W4298174377","https://openalex.org/W4298845604","https://openalex.org/W4319988532","https://openalex.org/W4394662461","https://openalex.org/W6631138648","https://openalex.org/W6638018090","https://openalex.org/W6666761814","https://openalex.org/W6669402789","https://openalex.org/W6675243623","https://openalex.org/W6677916085","https://openalex.org/W6683845664","https://openalex.org/W6695011786","https://openalex.org/W6703533685","https://openalex.org/W6727252785","https://openalex.org/W6727349600","https://openalex.org/W6731334075","https://openalex.org/W6740879895","https://openalex.org/W6741002519","https://openalex.org/W6748440607","https://openalex.org/W6759193872","https://openalex.org/W6775686901","https://openalex.org/W6780225908","https://openalex.org/W6849896277","https://openalex.org/W6863618527","https://openalex.org/W6999387429"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W4381094582","https://openalex.org/W1978893398","https://openalex.org/W1977906818","https://openalex.org/W2201908702","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W2600085362"],"abstract_inverted_index":{"The":[0,252],"reinforcement":[1,271],"learning":[2,44,73,89,111,114,136,189,200,272],"(RL)":[3],"community":[4],"has":[5],"made":[6],"great":[7],"strides":[8],"in":[9,87,122,193,205,268],"designing":[10],"algorithms":[11,21,115],"capable":[12],"of":[13,72,100,108,125,141,146,163,172,195,208,226,258,265],"exceeding":[14],"human":[15,232],"performance":[16,198,247,261],"on":[17,156,187,199,248,262],"specific":[18],"tasks.":[19],"These":[20],"are":[22],"mostly":[23],"trained":[24,63,219],"one":[25,59,77],"task":[26,32,60,174],"at":[27,82,160],"the":[28,43,58,70,98,105,123,135,142,147,152,161,170,176,188,196,239,259,269],"time,":[29],"each":[30,49,53,173],"new":[31,38],"requiring":[33],"to":[34,74,127,134,154,167,175,201],"train":[35],"a":[36,92,109,184,206,217,223,242,263],"brand":[37],"agent":[39,54,244],"instance.":[40],"This":[41,150,191],"means":[42],"algorithm":[45,153],"is":[46,51,90],"general,":[47],"but":[48,78],"solution":[50],"not;":[52],"can":[55,116],"only":[56],"solve":[57],"it":[61],"was":[62,238],"on.":[64],"In":[65],"this":[66,237,249],"work,":[67],"we":[68],"study":[69],"problem":[71],"master":[75],"not":[76],"multiple":[79,101],"sequentialdecision":[80],"tasks":[81,102,121,126,130,159,182,267],"once.":[83],"A":[84],"general":[85],"issue":[86],"multi-task":[88,250],"that":[91,180,229],"balance":[93],"must":[94],"be":[95],"found":[96],"between":[97],"needs":[99],"competing":[103],"for":[104,138],"limited":[106],"resources":[107],"single":[110,218,224,243],"system.":[112],"Many":[113],"get":[117],"distracted":[118],"by":[119],"certain":[120],"set":[124,207,225,264],"solve.":[128],"Such":[129],"appear":[131],"more":[132],"salient":[133,158],"process,":[137],"instance":[139],"because":[140],"density":[143],"or":[144],"magnitude":[145],"in-task":[148],"rewards.":[149],"causes":[151],"focus":[155],"those":[157],"expense":[162],"generality.":[164],"We":[165],"propose":[166],"automatically":[168],"adapt":[169],"contribution":[171],"agent\u2019s":[177],"updates,":[178],"so":[179],"all":[181,203],"have":[183],"similar":[185],"impact":[186],"dynamics.":[190],"resulted":[192],"state":[194,257],"art":[197,260],"play":[202],"games":[204],"57":[209],"diverse":[210],"Atari":[211],"games.":[212],"Excitingly,":[213],"our":[214,235],"method":[215],"learned":[216],"policy":[220],"-":[221,228],"with":[222],"weights":[227],"exceeds":[230],"median":[231],"performance.":[233],"To":[234],"knowledge,":[236],"first":[240],"time":[241],"surpassed":[245],"human-level":[246],"domain.":[251],"same":[253],"approach":[254],"also":[255],"demonstrated":[256],"30":[266],"3D":[270],"platform":[273],"DeepMind":[274],"Lab.":[275]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":52},{"year":2020,"cited_by_count":43},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}