{"id":"https://openalex.org/W2991420892","doi":null,"title":"Adaptive Auxiliary Task Weighting for Reinforcement Learning","display_name":"Adaptive Auxiliary Task Weighting for Reinforcement Learning","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2991420892","mag":"2991420892"},"language":"en","primary_location":{"id":"mag:2991420892","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/2019/file/0e900ad84f63618452210ab8baae0218-Paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5103223385","display_name":"Xingyu Lin","orcid":"https://orcid.org/0000-0002-2454-2520","observed_orcids":["https://orcid.org/0000-0002-2454-2520"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingyu Lin","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":"https://orcid.org/0000-0002-2454-2520","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068193480","display_name":"Harjatin Singh Baweja","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harjatin Singh Baweja","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067346459","display_name":"George A. Kantor","orcid":"https://orcid.org/0000-0001-7088-8533","observed_orcids":["https://orcid.org/0000-0001-7088-8533"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Kantor","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":"https://orcid.org/0000-0001-7088-8533","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133597454","display_name":"David Held","orcid":"https://orcid.org/0000-0003-0537-1508","observed_orcids":["https://orcid.org/0000-0003-0537-1508"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Held","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":"https://orcid.org/0000-0003-0537-1508","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":4.4269,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.95477786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"4772","last_page":"4783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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":0.0,"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/auxiliary-tasks","display_name":"auxiliary tasks","score":0.828000009059906},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.7409999966621399},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.8069999814033508},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"knowledge transfer","score":0.5979999899864197},{"id":"https://openalex.org/keywords/gradient-direction","display_name":"gradient direction","score":0.5839999914169312},{"id":"https://openalex.org/keywords/high-dimensional-observations","display_name":"high-dimensional observations","score":0.6430000066757202},{"id":"https://openalex.org/keywords/training-acceleration","display_name":"training acceleration","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8908343315124512},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8283005356788635},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7535288333892822},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7127318978309631},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6660003662109375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5611565709114075},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.536285400390625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4614518880844116},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.43266117572784424},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4214332401752472},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.41572606563568115},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.06837818026542664},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06616783142089844},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2991420892","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/2019/file/0e900ad84f63618452210ab8baae0218-Paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W99485931","https://openalex.org/W1520997877","https://openalex.org/W1536680647","https://openalex.org/W2097451239","https://openalex.org/W2119076496","https://openalex.org/W2144752499","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155027007","https://openalex.org/W2293467699","https://openalex.org/W2563830277","https://openalex.org/W2624871570","https://openalex.org/W2766447205","https://openalex.org/W2767286446","https://openalex.org/W2796835114","https://openalex.org/W2798512429","https://openalex.org/W2803576056","https://openalex.org/W2803767077","https://openalex.org/W2913340405","https://openalex.org/W2963677766"],"related_works":["https://openalex.org/W4307473887","https://openalex.org/W4415909442","https://openalex.org/W2551887912","https://openalex.org/W4224703920","https://openalex.org/W2965307502","https://openalex.org/W4323922096","https://openalex.org/W2989941044","https://openalex.org/W3133087405","https://openalex.org/W3181983673","https://openalex.org/W7133212814"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,35,67],"is":[2,28,84],"known":[3],"to":[4,11,49,75,102,132],"be":[5],"sample":[6],"inefficient,":[7],"preventing":[8],"its":[9],"application":[10],"many":[12],"real-world":[13],"problems,":[14],"especially":[15],"with":[16],"high":[17],"dimensional":[18],"observations":[19],"like":[20],"images.":[21],"Transferring":[22],"knowledge":[23],"from":[24],"other":[25],"auxiliary":[26,41,57,73,90,125,138],"tasks":[27,42,74,91,126],"a":[29,64,121],"powerful":[30],"tool":[31],"for":[32,79],"improving":[33],"the":[34,38,50,87,98,104,107],"efficiency.":[36],"However,":[37],"usage":[39],"of":[40,106,123,136],"has":[43],"been":[44],"limited":[45],"so":[46],"far":[47],"due":[48],"difficulty":[51],"in":[52,97,112],"selecting":[53],"and":[54,127],"combining":[55],"different":[56,72,124],"tasks.":[58],"In":[59],"this":[60],"work,":[61],"we":[62],"propose":[63],"principled":[65],"online":[66],"algorithm":[68,117],"that":[69,89,115],"dynamically":[70],"combines":[71],"speed":[76],"up":[77],"training":[78],"reinforcement":[80],"learning.":[81],"Our":[82],"method":[83],"based":[85],"on":[86],"idea":[88],"should":[92],"provide":[93],"gradient":[94],"directions":[95],"that,":[96],"long":[99],"term,":[100],"help":[101],"decrease":[103],"loss":[105],"main":[108],"task.":[109],"We":[110],"show":[111],"various":[113],"environments":[114],"our":[116],"can":[118],"effectively":[119],"combine":[120],"variety":[122],"achieves":[128],"significant":[129],"speedup":[130],"compared":[131],"previous":[133],"heuristic":[134],"approches":[135],"adapting":[137],"task":[139],"weights.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":8}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-12-05T00:00:00"}