{"id":"https://openalex.org/W4383097530","doi":"https://doi.org/10.1109/icra48891.2023.10160626","title":"Meta-Reinforcement Learning via Language Instructions","display_name":"Meta-Reinforcement Learning via Language Instructions","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383097530","doi":"https://doi.org/10.1109/icra48891.2023.10160626"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5060444894","display_name":"Zhenshan Bing","orcid":"https://orcid.org/0000-0002-0896-2517"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Zhenshan Bing","raw_affiliation_strings":["Technical University of Munich,Department of Informatics,Germany","Department of Informatics, Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Department of Informatics,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067814971","display_name":"Alexander Koch","orcid":"https://orcid.org/0000-0002-3510-9669"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Koch","raw_affiliation_strings":["Technical University of Munich,Department of Informatics,Germany","Department of Informatics, Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Department of Informatics,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073985865","display_name":"Xiangtong Yao","orcid":"https://orcid.org/0000-0003-2556-3072"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xiangtong Yao","raw_affiliation_strings":["Technical University of Munich,Department of Informatics,Germany","Department of Informatics, Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Department of Informatics,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768452","display_name":"Kai Huang","orcid":"https://orcid.org/0000-0003-0359-7810"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Huang","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University,China","School of Data and Computer Science, Sun Yat-sen University, China"],"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063781430","display_name":"Alois Knoll","orcid":"https://orcid.org/0000-0003-4840-076X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":["Technical University of Munich,Department of Informatics,Germany","Department of Informatics, Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Department of Informatics,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5060444894"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":1.9231,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88570421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5985","last_page":"5991"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9879999756813049,"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":0.9035363793373108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8534443378448486},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7325596809387207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6170210242271423},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5685945153236389},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.507979691028595},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4505893290042877},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.4483361840248108},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.44573473930358887},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.41398653388023376},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38364243507385254},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3807166814804077},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12173682451248169}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9035363793373108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8534443378448486},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7325596809387207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6170210242271423},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5685945153236389},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.507979691028595},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4505893290042877},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.4483361840248108},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.44573473930358887},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41398653388023376},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38364243507385254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3807166814804077},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12173682451248169},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G876240350","display_name":null,"funder_award_id":"DIK0249","funder_id":"https://openalex.org/F4320323061","funder_display_name":"Bayerisches Staatsministerium f\u00fcr Wirtschaft, Infrastruktur, Verkehr und Technologie"}],"funders":[{"id":"https://openalex.org/F4320323061","display_name":"Bayerisches Staatsministerium f\u00fcr Wirtschaft, Infrastruktur, Verkehr und Technologie","ror":"https://ror.org/00rspzk45"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1512866498","https://openalex.org/W1771410628","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2250539671","https://openalex.org/W2509374375","https://openalex.org/W2578206533","https://openalex.org/W2604763608","https://openalex.org/W2772709170","https://openalex.org/W2798705390","https://openalex.org/W2890344110","https://openalex.org/W2904246096","https://openalex.org/W2938321354","https://openalex.org/W2952526277","https://openalex.org/W2963211300","https://openalex.org/W2981030070","https://openalex.org/W2981344907","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3031840745","https://openalex.org/W3036233998","https://openalex.org/W3098201885","https://openalex.org/W3175584021","https://openalex.org/W3188527995","https://openalex.org/W3207832698","https://openalex.org/W3210966861","https://openalex.org/W3213538577","https://openalex.org/W4226370791","https://openalex.org/W4283365039","https://openalex.org/W4285294350","https://openalex.org/W4296425656","https://openalex.org/W4298230560","https://openalex.org/W4300799055","https://openalex.org/W4300971732","https://openalex.org/W4312301659","https://openalex.org/W4382318723","https://openalex.org/W6630802251","https://openalex.org/W6638018090","https://openalex.org/W6682849425","https://openalex.org/W6729433768","https://openalex.org/W6736057607","https://openalex.org/W6740801417","https://openalex.org/W6746177919","https://openalex.org/W6746684068","https://openalex.org/W6757592117","https://openalex.org/W6760439459","https://openalex.org/W6760698134","https://openalex.org/W6769596995","https://openalex.org/W6772005887","https://openalex.org/W6784155536","https://openalex.org/W6799214972"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W3130669838","https://openalex.org/W2785397462","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2891227010"],"abstract_inverted_index":{"Although":[0],"deep":[1],"reinforcement":[2,42],"learning":[3,10,39,55,117],"has":[4],"recently":[5,99],"been":[6],"very":[7],"successful":[8],"at":[9,185],"complex":[11],"behaviors,":[12],"it":[13,147,168],"requires":[14],"a":[15,22,70,98,109,154],"tremendous":[16],"amount":[17],"of":[18,25,36,41,116,140,175],"data":[19],"to":[20,68,93,136,150],"learn":[21,69],"task.":[23],"One":[24],"the":[26,34,37,45,49,54,59,74,95,114,127,133,141,144,162],"fundamental":[27],"reasons":[28],"causing":[29],"this":[30,105],"limitation":[31],"lies":[32],"in":[33,53,122,153,173],"nature":[35],"trial-and-error":[38,155],"paradigm":[40],"learning,":[43],"where":[44],"agent":[46],"communicates":[47],"with":[48,119],"environment":[50],"and":[51,65,102,167,177],"pro-gresses":[52],"only":[56],"relying":[57],"on":[58,143,161],"reward":[60],"signal.":[61],"This":[62],"is":[63,97],"implicit":[64],"rather":[66],"insufficient":[67],"task":[71,152,179],"well.":[72],"On":[73,126],"con-trary,":[75],"humans":[76],"are":[77,183],"usually":[78],"taught":[79],"new":[80],"skills":[81,118],"via":[82],"natural":[83],"language":[84,87,120,134],"instructions.":[85],"Utilizing":[86],"instructions":[88,121,135],"for":[89],"robotic":[90,163],"motion":[91],"control":[92],"improve":[94],"adaptability":[96],"emerged":[100],"topic":[101],"challenging.":[103],"In":[104],"paper,":[106],"we":[107],"present":[108],"meta-RL":[110],"algorithm":[111,131,160],"that":[112],"addresses":[113],"challenge":[115],"multiple":[123],"manipulation":[124,164],"tasks.":[125],"one":[128],"hand,":[129,146],"our":[130,159],"utilizes":[132],"shape":[137],"its":[138],"in-terpretation":[139],"task,":[142],"other":[145],"still":[148],"learns":[149],"solve":[151],"process.":[156],"We":[157],"evaluate":[158],"benchmark":[165],"(Meta-World)":[166],"significantly":[169],"outperforms":[170],"state-of-the-art":[171],"methods":[172],"terms":[174],"training":[176],"testing":[178],"success":[180],"rates.":[181],"Codes":[182],"available":[184],"https://tumi6robot.wixsite.com/million.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}