{"id":"https://openalex.org/W2966461828","doi":"https://doi.org/10.24963/ijcai.2019/387","title":"Meta Reinforcement Learning with Task Embedding and Shared Policy","display_name":"Meta Reinforcement Learning with Task Embedding and Shared Policy","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2966461828","doi":"https://doi.org/10.24963/ijcai.2019/387","mag":"2966461828"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/387","doi":"https://doi.org/10.24963/ijcai.2019/387","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/387","pdf_url":"https://www.ijcai.org/proceedings/2019/0387.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2019/0387.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016571508","display_name":"Lin Lan","orcid":"https://orcid.org/0000-0001-7363-1143","observed_orcids":["https://orcid.org/0000-0001-7363-1143"]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Lan","raw_affiliation_strings":["MOE NSKEY Lab, Xi\u2019an Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE NSKEY Lab, Xi\u2019an Jiaotong University, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103196797","display_name":"Zhenguo Li","orcid":"https://orcid.org/0000-0002-8492-3069","observed_orcids":["https://orcid.org/0000-0002-8492-3069"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenguo Li","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075845093","display_name":"Xiaohong Guan","orcid":"https://orcid.org/0000-0002-8826-0362","observed_orcids":["https://orcid.org/0000-0002-8826-0362"]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]},{"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":"Xiaohong Guan","raw_affiliation_strings":["Department of Automation and NLIST Lab, Tsinghua University, China","MOE NSKEY Lab, Xi\u2019an Jiaotong University, China","Shenzhen Research School, Xi\u2019an Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation and NLIST Lab, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"MOE NSKEY Lab, Xi\u2019an Jiaotong University, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Shenzhen Research School, Xi\u2019an Jiaotong University, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022240408","display_name":"Pinghui Wang","orcid":"https://orcid.org/0000-0001-5779-6108","observed_orcids":["https://orcid.org/0000-0001-5779-6108","https://orcid.org/0000-0002-1434-837X"]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pinghui Wang","raw_affiliation_strings":["MOE NSKEY Lab, Xi\u2019an Jiaotong University, China","Shenzhen Research School, Xi\u2019an Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE NSKEY Lab, Xi\u2019an Jiaotong University, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Shenzhen Research School, Xi\u2019an Jiaotong University, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.284,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.91730483,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2794","last_page":"2800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0008999999845400453,"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/T10906","display_name":"AI-based Problem Solving and Planning","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/meta-reinforcement-learning","display_name":"meta-reinforcement learning","score":0.9359999895095825},{"id":"https://openalex.org/keywords/task-embeddings","display_name":"task embeddings","score":0.9750000238418579},{"id":"https://openalex.org/keywords/data-efficiency","display_name":"data efficiency","score":0.5870000123977661},{"id":"https://openalex.org/keywords/task-similarity","display_name":"task similarity","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.852500319480896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8307033181190491},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7014818787574768},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6063677668571472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5657931566238403},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.556977391242981},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5295950770378113},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.5254982113838196},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48674559593200684},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4555337429046631},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.41821444034576416},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32470279932022095},{"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/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.24963/ijcai.2019/387","doi":"https://doi.org/10.24963/ijcai.2019/387","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/387","pdf_url":"https://www.ijcai.org/proceedings/2019/0387.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.06527","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.06527","pdf_url":"https://arxiv.org/pdf/1905.06527","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1905.06527","doi":"https://doi.org/10.48550/arxiv.1905.06527","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.06527","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/387","doi":"https://doi.org/10.24963/ijcai.2019/387","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/387","pdf_url":"https://www.ijcai.org/proceedings/2019/0387.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1067324075","display_name":null,"funder_award_id":"U1736205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2453883782","display_name":null,"funder_award_id":"61603290","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2577194348","display_name":null,"funder_award_id":"LGG18F020016","funder_id":"https://openalex.org/F4320336567","funder_display_name":"Natural Science Basic Research Program of Shaanxi Province"},{"id":"https://openalex.org/G6989792634","display_name":null,"funder_award_id":"U1736205, 61603290","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336567","display_name":"Natural Science Basic Research Program of Shaanxi Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2966461828.pdf","grobid_xml":"https://content.openalex.org/works/W2966461828.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1757796397","https://openalex.org/W1959608418","https://openalex.org/W2119717200","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2312609093","https://openalex.org/W2578206533","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2606433045","https://openalex.org/W2624871570","https://openalex.org/W2734377693","https://openalex.org/W2736601468","https://openalex.org/W2742093937","https://openalex.org/W2762872434","https://openalex.org/W2765602917","https://openalex.org/W2785397462","https://openalex.org/W2787387965","https://openalex.org/W2787501667","https://openalex.org/W2792305967","https://openalex.org/W2794757725","https://openalex.org/W2803767077","https://openalex.org/W2806029332","https://openalex.org/W2808682055","https://openalex.org/W2809290718","https://openalex.org/W2809469215","https://openalex.org/W2890260778","https://openalex.org/W2903630557","https://openalex.org/W2951004968","https://openalex.org/W2963176272","https://openalex.org/W2963286043","https://openalex.org/W2964161785","https://openalex.org/W4214717370","https://openalex.org/W6803771590","https://openalex.org/W6834709193","https://openalex.org/W6863252125","https://openalex.org/W6863318804"],"related_works":["https://openalex.org/W4226463308","https://openalex.org/W3120288532","https://openalex.org/W3009692840","https://openalex.org/W7207732984","https://openalex.org/W4395098237","https://openalex.org/W3175784873","https://openalex.org/W7134148884","https://openalex.org/W3131310681","https://openalex.org/W7124517945","https://openalex.org/W2789543555"],"abstract_inverted_index":{"Despite":[0],"significant":[1],"progress,":[2],"deep":[3],"reinforcement":[4],"learning":[5,168],"(RL)":[6],"suffers":[7],"from":[8,21],"data-inefficiency":[9],"and":[10,61,66,80,100,151,173,176],"limited":[11],"generalization.":[12],"Recent":[13],"efforts":[14],"apply":[15],"meta-learning":[16],"to":[17,76,81,83,91,103,122,179,181,187],"learn":[18,77,142],"a":[19,22,29,51,110,125,133,143],"meta-learner":[20,121],"set":[23],"of":[24],"RL":[25],"tasks":[26,44,79,150,161,175],"such":[27],"that":[28,163],"novel":[30,84,174],"but":[31],"related":[32],"task":[33,111,126,134,154],"could":[34],"be":[35],"solved":[36],"quickly.":[37],"Though":[38],"specific":[39,65,107],"in":[40,45],"some":[41],"ways,":[42],"different":[43,70],"meta-RL":[46,56],"are":[47],"generally":[48],"similar":[49],"at":[50],"high":[52],"level.":[53],"However,":[54],"most":[55],"methods":[57],"do":[58],"not":[59],"explicitly":[60],"adequately":[62],"model":[63],"the":[64,93,97,106,113],"shared":[67,94,147],"information":[68,95,108],"among":[69],"tasks,":[71],"which":[72,131,145],"limits":[73],"their":[74],"ability":[75],"training":[78,172],"generalize":[82],"tasks.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89,117,141],"propose":[90],"capture":[92],"on":[96,112,137,153,158,170],"one":[98],"hand":[99],"meta-learn":[101],"how":[102],"quickly":[104,123],"abstract":[105],"about":[109],"other":[114],"hand.":[115],"Methodologically,":[116],"train":[118],"an":[119],"SGD":[120],"optimize":[124],"encoder":[127],"for":[128],"each":[129],"task,":[130],"generates":[132],"embedding":[135],"based":[136],"past":[138],"experience.":[139],"Meanwhile,":[140],"policy":[144],"is":[146],"across":[148],"all":[149],"conditioned":[152],"embeddings.":[155],"Empirical":[156],"results":[157],"four":[159],"simulated":[160],"demonstrate":[162],"our":[164],"method":[165],"has":[166],"better":[167],"capacity":[169],"both":[171],"attains":[177],"up":[178],"3":[180],"4":[182],"times":[183],"higher":[184],"returns":[185],"compared":[186],"baselines.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-08-13T00:00:00"}