{"id":"https://openalex.org/W3109396871","doi":"https://doi.org/10.1109/icra48506.2021.9561219","title":"Double Meta-Learning for Data Efficient Policy Optimization in Non-Stationary Environments","display_name":"Double Meta-Learning for Data Efficient Policy Optimization in Non-Stationary Environments","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3109396871","doi":"https://doi.org/10.1109/icra48506.2021.9561219","mag":"3109396871"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.10714","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062177559","display_name":"Elahe Aghapour","orcid":"https://orcid.org/0000-0002-8218-6704"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elahe Aghapour","raw_affiliation_strings":["University of Southern California,Department of Computer Science,USA","University of Southern California, Department of Computer Science, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Computer Science,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Department of Computer Science, USA#TAB#","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002752114","display_name":"Nora Ayanian","orcid":"https://orcid.org/0000-0002-8394-6912"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nora Ayanian","raw_affiliation_strings":["University of Southern California,Department of Computer Science,USA","University  of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Computer Science,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1464,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32400839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983999729156494,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983999729156494,"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":0.9973999857902527,"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/T12676","display_name":"Machine Learning and ELM","score":0.9943000078201294,"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":0.888159990310669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7852907180786133},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.7267137765884399},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6517001986503601},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5735573768615723},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5701866745948792},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5620553493499756},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5327622294425964},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4711797535419464},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.41857272386550903},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08971777558326721},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08798983693122864}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.888159990310669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852907180786133},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.7267137765884399},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6517001986503601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5735573768615723},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5701866745948792},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5620553493499756},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5327622294425964},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4711797535419464},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.41857272386550903},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08971777558326721},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08798983693122864},{"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/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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9561219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.10714","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.10714","pdf_url":"https://arxiv.org/pdf/2011.10714","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,"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":"mag:3109396871","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.10714","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,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.10714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.10714","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.10714","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.10714","pdf_url":"https://arxiv.org/pdf/2011.10714","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3109396871.pdf","grobid_xml":"https://content.openalex.org/works/W3109396871.grobid-xml"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1868559974","https://openalex.org/W1923344279","https://openalex.org/W2100235553","https://openalex.org/W2119717200","https://openalex.org/W2121103318","https://openalex.org/W2134491302","https://openalex.org/W2136503687","https://openalex.org/W2137825550","https://openalex.org/W2140135625","https://openalex.org/W2188233853","https://openalex.org/W2257979135","https://openalex.org/W2281096776","https://openalex.org/W2290354866","https://openalex.org/W2416041116","https://openalex.org/W2575705757","https://openalex.org/W2578206533","https://openalex.org/W2604763608","https://openalex.org/W2742093937","https://openalex.org/W2743381431","https://openalex.org/W2753160622","https://openalex.org/W2762872434","https://openalex.org/W2768607686","https://openalex.org/W2787501667","https://openalex.org/W2789824229","https://openalex.org/W2794363191","https://openalex.org/W2794757725","https://openalex.org/W2795900505","https://openalex.org/W2892230114","https://openalex.org/W2942608247","https://openalex.org/W2962872206","https://openalex.org/W2962899390","https://openalex.org/W2963025296","https://openalex.org/W2963303956","https://openalex.org/W2963547174","https://openalex.org/W2963581679","https://openalex.org/W2963775850","https://openalex.org/W2963809569","https://openalex.org/W2963846183","https://openalex.org/W2964093801","https://openalex.org/W2964161785","https://openalex.org/W2964173023","https://openalex.org/W2996148148","https://openalex.org/W3195133498","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6678367057","https://openalex.org/W6680139899","https://openalex.org/W6680657880","https://openalex.org/W6682849425","https://openalex.org/W6686996450","https://openalex.org/W6696324988","https://openalex.org/W6717367658","https://openalex.org/W6728252718","https://openalex.org/W6729433768","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6740033195","https://openalex.org/W6742288159","https://openalex.org/W6743661861","https://openalex.org/W6746062806","https://openalex.org/W6747943641","https://openalex.org/W6748331328","https://openalex.org/W6748519856","https://openalex.org/W6748817170","https://openalex.org/W6749745641","https://openalex.org/W6750254146","https://openalex.org/W6754471908","https://openalex.org/W6755365793","https://openalex.org/W6755476724","https://openalex.org/W6757223306","https://openalex.org/W6769269530","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3205801758","https://openalex.org/W3095858279","https://openalex.org/W2923504512","https://openalex.org/W2949945034","https://openalex.org/W3197842098","https://openalex.org/W3198015624","https://openalex.org/W3200201724","https://openalex.org/W3208886368","https://openalex.org/W3109198942","https://openalex.org/W3175784873","https://openalex.org/W2963922698","https://openalex.org/W2995957611","https://openalex.org/W2962928691","https://openalex.org/W3125579273","https://openalex.org/W3108083844","https://openalex.org/W3091601240","https://openalex.org/W3127945829","https://openalex.org/W2949555518","https://openalex.org/W3130806609","https://openalex.org/W3089433505"],"abstract_inverted_index":{"We":[0],"are":[1,48,122],"interested":[2],"in":[3,27,167],"learning":[4,16,20,29,42,54,66,76,94,119,177],"models":[5],"of":[6,33,101,117,130,146,175,185],"non-stationary":[7,103,132,169],"environments,":[8],"which":[9,40],"can":[10,22,163],"be":[11,106],"framed":[12],"as":[13],"a":[14,31,84,92,102,168],"multitask":[15,28],"problem.":[17],"Model-free":[18],"reinforcement":[19],"algorithms":[21],"achieve":[23],"good":[24],"asymptotic":[25,183],"performance":[26,184],"at":[30],"cost":[32],"extensive":[34],"sampling,":[35],"due":[36],"to":[37,96,105,113,124],"their":[38],"approach,":[39],"requires":[41],"from":[43],"scratch.":[44],"While":[45],"model-based":[46,118,176],"approaches":[47,178],"among":[49],"the":[50,68,80,98,114,128,131,135,142,147,165,172,181],"most":[51],"data":[52,152,173],"efficient":[53],"algorithms,":[55],"they":[56],"still":[57],"struggle":[58],"with":[59,171],"complex":[60],"tasks":[61],"and":[62,70,134],"model":[63,100,139,145],"uncertainties.":[64],"Meta-reinforcement":[65],"addresses":[67],"efficiency":[69,116,174],"generalization":[71],"challenges":[72],"on":[73],"multi":[74],"task":[75],"by":[77],"quickly":[78],"leveraging":[79],"meta-prior":[81],"policy":[82,166],"for":[83,108,153],"new":[85],"task.":[86],"In":[87],"this":[88],"paper,":[89],"we":[90,121],"propose":[91],"meta-reinforcement":[93,187],"approach":[95],"learn":[97],"dynamic":[99,138,144],"environment":[104,133,148,170],"used":[107],"meta-policy":[109,136,154],"optimization":[110],"later.":[111],"Due":[112],"sample":[115],"methods,":[120],"able":[123],"simultaneously":[125],"train":[126],"both":[127],"meta-model":[129],"until":[137],"convergence.":[140],"Then,":[141],"meta-learned":[143],"will":[149],"generate":[150],"simulated":[151],"optimization.":[155],"Our":[156],"experiment":[157],"demonstrates":[158],"that":[159],"our":[160],"proposed":[161],"method":[162],"meta-learn":[164],"while":[179],"achieving":[180],"high":[182],"model-free":[186],"learning.":[188]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}