{"id":"https://openalex.org/W2903685241","doi":"https://doi.org/10.1609/aaai.v33i01.33015933","title":"Self-Supervised Mixture-of-Experts by Uncertainty Estimation","display_name":"Self-Supervised Mixture-of-Experts by Uncertainty Estimation","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2903685241","doi":"https://doi.org/10.1609/aaai.v33i01.33015933","mag":"2903685241"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33015933","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015933","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33015933","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102591905","display_name":"Zhuobin Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuobin Zheng","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101456902","display_name":"Chun Yuan","orcid":"https://orcid.org/0000-0002-3590-6676"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yuan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040802661","display_name":"Xinrui Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinrui Zhu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054238848","display_name":"Zhihui Lin","orcid":"https://orcid.org/0000-0003-0949-0635"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihui Lin","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021760829","display_name":"Yangyang Cheng","orcid":"https://orcid.org/0000-0003-4991-6610"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyang Cheng","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057480166","display_name":"Shi Cheng","orcid":"https://orcid.org/0000-0003-2079-6344"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Shi","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031297718","display_name":"Jiahui Ye","orcid":"https://orcid.org/0000-0002-6558-6925"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Ye","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3989,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.66053032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"33","issue":"01","first_page":"5933","last_page":"5940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9894000291824341,"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":0.9894000291824341,"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":0.9661999940872192,"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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9430000185966492,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7791509032249451},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.75513756275177},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7355093955993652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.73316890001297},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6931843757629395},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6334341764450073},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5242017507553101},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5149672627449036},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3165208697319031},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12403711676597595},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08540913462638855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791509032249451},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.75513756275177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7355093955993652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.73316890001297},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6931843757629395},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6334341764450073},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5242017507553101},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5149672627449036},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3165208697319031},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12403711676597595},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08540913462638855},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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.v33i01.33015933","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015933","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/4544","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4544","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4544/4422","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/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33015933","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015933","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":[{"id":"https://openalex.org/G4469221245","display_name":null,"funder_award_id":"U1833101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W158722652","https://openalex.org/W1522301498","https://openalex.org/W1560021816","https://openalex.org/W2134197408","https://openalex.org/W2145339207","https://openalex.org/W2150884987","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2280163991","https://openalex.org/W2462906003","https://openalex.org/W2558634851","https://openalex.org/W2560321925","https://openalex.org/W2575705757","https://openalex.org/W2581624817","https://openalex.org/W2586067474","https://openalex.org/W2610550445","https://openalex.org/W2614839826","https://openalex.org/W2735995851","https://openalex.org/W2766447205","https://openalex.org/W2797527950","https://openalex.org/W2807908072","https://openalex.org/W2962824366","https://openalex.org/W2963009616","https://openalex.org/W2963238274","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964200634","https://openalex.org/W4214717370","https://openalex.org/W4293718192","https://openalex.org/W4294568686","https://openalex.org/W4298174377","https://openalex.org/W4298438771","https://openalex.org/W4319988532","https://openalex.org/W4394662669","https://openalex.org/W6631190155","https://openalex.org/W6635327058","https://openalex.org/W6656844882","https://openalex.org/W6680171673","https://openalex.org/W6682198495","https://openalex.org/W6683153233","https://openalex.org/W6684205842","https://openalex.org/W6695011786","https://openalex.org/W6715501732","https://openalex.org/W6740879895","https://openalex.org/W6743292961","https://openalex.org/W6752012111","https://openalex.org/W6759193872"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W2922073769","https://openalex.org/W4378510483","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4221142204","https://openalex.org/W4378505373"],"abstract_inverted_index":{"Learning":[0,19],"related":[1,77,227],"tasks":[2,78,125],"in":[3,17,32,40,129],"various":[4],"domains":[5],"and":[6,28,38,96,107,118,132,166,201,215,222],"transferring":[7],"exploited":[8],"knowledge":[9,122],"to":[10,30,72,99,116,154,159],"new":[11],"situations":[12],"is":[13,88,152,191],"a":[14,64,74,148,156],"significant":[15],"challenge":[16],"Reinforcement":[18],"(RL).":[20],"However,":[21],"most":[22],"RL":[23],"algorithms":[24],"are":[25],"data":[26],"inefficient":[27],"fail":[29],"generalize":[31],"complex":[33],"environments,":[34],"limiting":[35],"their":[36],"adaptability":[37],"applicability":[39],"multi-task":[41,234],"scenarios.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"propose":[47],"SelfSupervised":[48],"Mixture-of-Experts":[49],"(SUM),":[50],"an":[51],"effective":[52],"algorithm":[53],"driven":[54],"by":[55,80,90,169,219],"predictive":[56,91],"uncertainty":[57,92,171],"estimation":[58,93],"for":[59],"multitask":[60],"RL.":[61],"SUM":[62],"utilizes":[63],"multi-head":[65],"agent":[66,115],"with":[67],"shared":[68],"parameters":[69],"as":[70,145,185],"experts":[71,175,204],"learn":[73],"series":[75],"of":[76,135,142,188,203],"simultaneously":[79],"Deep":[81],"Deterministic":[82],"Policy":[83],"Gradient":[84],"(DDPG).":[85],"Each":[86],"expert":[87,136,158,183],"extended":[89,230],"on":[94,229],"known":[95],"unknown":[97],"states":[98],"enhance":[100],"the":[101,108,114,120,133,170,174,181,186],"Q-value":[102],"evaluation":[103],"capacity":[104],"against":[105],"overfitting":[106],"overall":[109],"generalization":[110],"ability.":[111],"These":[112],"enable":[113],"capture":[117],"diffuse":[119],"common":[121,146],"across":[123,138],"different":[124,206],"improving":[126],"sample":[127],"efficiency":[128],"each":[130,161],"task":[131],"effectiveness":[134],"scheduling":[137],"multiple":[139],"tasks.":[140],"Instead":[141],"task-specific":[143],"design":[144],"MoEs,":[147],"self-supervised":[149],"gating":[150],"network":[151],"adopted":[153],"determine":[155],"potential":[157],"handle":[160],"interaction":[162],"from":[163,173],"unseen":[164],"environments":[165],"calibrated":[167],"completely":[168],"feedback":[172],"without":[176],"explicit":[177],"supervision.":[178],"To":[179],"alleviate":[180],"imbalanced":[182],"utilization":[184],"crux":[187],"MoE,":[189],"optimization":[190],"accomplished":[192],"via":[193],"decayedmasked":[194],"experience":[195],"replay,":[196],"which":[197],"encourages":[198],"both":[199],"diversification":[200],"specialization":[202],"during":[205],"periods.":[207],"We":[208],"demonstrate":[209],"that":[210],"our":[211],"approach":[212],"learns":[213],"faster":[214],"achieves":[216],"better":[217],"performance":[218],"efficient":[220],"transfer":[221],"robust":[223],"generalization,":[224],"outperforming":[225],"several":[226],"methods":[228],"OpenAI":[231],"Gym\u2019s":[232],"MuJoCo":[233],"environments.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}