{"id":"https://openalex.org/W4383097601","doi":"https://doi.org/10.1109/icra48891.2023.10160764","title":"Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning","display_name":"Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383097601","doi":"https://doi.org/10.1109/icra48891.2023.10160764"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160764","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/A5102712322","display_name":"Zheng Wu","orcid":"https://orcid.org/0000-0003-0811-6385"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Wu","raw_affiliation_strings":["University of California, Berkeley,Berkeley,CA,USA","University of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley,Berkeley,CA,USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046598816","display_name":"Yichen Xie","orcid":"https://orcid.org/0000-0002-0974-5979"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yichen Xie","raw_affiliation_strings":["University of California, Berkeley,Berkeley,CA,USA","University of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley,Berkeley,CA,USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017678179","display_name":"Wenzhao Lian","orcid":"https://orcid.org/0000-0002-0995-8229"},"institutions":[{"id":"https://openalex.org/I4210105824","display_name":"Intrinsic LifeSciences (United States)","ror":"https://ror.org/01maah330","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105824"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenzhao Lian","raw_affiliation_strings":["Intrinsic Innovation LLC,Mountain View,CA,USA","Intrinsic Innovation LLC, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intrinsic Innovation LLC,Mountain View,CA,USA","institution_ids":["https://openalex.org/I4210105824"]},{"raw_affiliation_string":"Intrinsic Innovation LLC, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210105824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709173","display_name":"Changhao Wang","orcid":"https://orcid.org/0000-0002-5753-1991"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changhao Wang","raw_affiliation_strings":["University of California, Berkeley,Berkeley,CA,USA","University of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley,Berkeley,CA,USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039046784","display_name":"Yanjiang Guo","orcid":"https://orcid.org/0000-0001-5841-6170"},"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":"Yanjiang Guo","raw_affiliation_strings":["Tsinghua University,Beijing,China","Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611364","display_name":"Jianyu Chen","orcid":"https://orcid.org/0000-0001-7211-7927"},"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":"Jianyu Chen","raw_affiliation_strings":["Tsinghua University,Beijing,China","Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029642293","display_name":"Stefan Schaal","orcid":"https://orcid.org/0000-0001-5660-1874"},"institutions":[{"id":"https://openalex.org/I4210105824","display_name":"Intrinsic LifeSciences (United States)","ror":"https://ror.org/01maah330","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105824"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Schaal","raw_affiliation_strings":["Intrinsic Innovation LLC,Mountain View,CA,USA","Intrinsic Innovation LLC, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intrinsic Innovation LLC,Mountain View,CA,USA","institution_ids":["https://openalex.org/I4210105824"]},{"raw_affiliation_string":"Intrinsic Innovation LLC, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210105824"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064077634","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masayoshi Tomizuka","raw_affiliation_strings":["University of California, Berkeley,Berkeley,CA,USA","University of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley,Berkeley,CA,USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3767,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80903996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7169","last_page":"7175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9603999853134155,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.948199987411499,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/principle-of-compositionality","display_name":"Principle of compositionality","score":0.8705549240112305},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.854516863822937},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.8408035039901733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8051387667655945},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7421719431877136},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6853669285774231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5978305339813232},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5153276324272156},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5115907788276672},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.426535964012146},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4144662320613861},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4075581431388855},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11826005578041077}],"concepts":[{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.8705549240112305},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.854516863822937},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8408035039901733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051387667655945},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7421719431877136},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6853669285774231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5978305339813232},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5153276324272156},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5115907788276672},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.426535964012146},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4144662320613861},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4075581431388855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11826005578041077},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160764","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2112474089","https://openalex.org/W2128728535","https://openalex.org/W2214715755","https://openalex.org/W2526379199","https://openalex.org/W2604763608","https://openalex.org/W2605102758","https://openalex.org/W2620290674","https://openalex.org/W2781726626","https://openalex.org/W2788904251","https://openalex.org/W2810785043","https://openalex.org/W2914752403","https://openalex.org/W2945020056","https://openalex.org/W2951725892","https://openalex.org/W2953070460","https://openalex.org/W2964198579","https://openalex.org/W2968095426","https://openalex.org/W2970263828","https://openalex.org/W2979490629","https://openalex.org/W2980555752","https://openalex.org/W3035060554","https://openalex.org/W3088304681","https://openalex.org/W3101442004","https://openalex.org/W3120778962","https://openalex.org/W3130984490","https://openalex.org/W4214717370","https://openalex.org/W4225670345","https://openalex.org/W4287632120","https://openalex.org/W4289145571","https://openalex.org/W4297669644","https://openalex.org/W4300514939","https://openalex.org/W6733814495","https://openalex.org/W6745744936","https://openalex.org/W6748600884","https://openalex.org/W6751959828","https://openalex.org/W6762959241","https://openalex.org/W6764088478","https://openalex.org/W6767199790","https://openalex.org/W6769269530","https://openalex.org/W6779326418","https://openalex.org/W6785022050","https://openalex.org/W6809873821"],"related_works":["https://openalex.org/W3095531775","https://openalex.org/W1526190050","https://openalex.org/W4251923961","https://openalex.org/W2477397717","https://openalex.org/W2010490241","https://openalex.org/W2500457737","https://openalex.org/W4287025733","https://openalex.org/W3192500523","https://openalex.org/W4317425742","https://openalex.org/W4241382148"],"abstract_inverted_index":{"Humans":[0],"are":[1],"capable":[2],"of":[3,10,15,50,75],"abstracting":[4],"various":[5],"tasks":[6,30,103,124],"as":[7],"different":[8,73],"combinations":[9],"multiple":[11],"attributes.":[12],"This":[13],"perspective":[14],"compositionality":[16],"is":[17,63,80,98],"vital":[18],"for":[19],"human":[20],"rapid":[21],"learning":[22],"and":[23,104],"adaption":[24],"since":[25],"previous":[26],"experiences":[27],"from":[28],"related":[29],"can":[31],"be":[32],"combined":[33],"to":[34,45,121],"generalize":[35],"across":[36],"novel":[37],"compositional":[38,86,123],"settings.":[39],"In":[40],"this":[41],"work,":[42],"we":[43],"aim":[44],"achieve":[46],"zero-shot":[47,127],"policy":[48,119],"generalization":[49,79,120],"Reinforcement":[51],"Learning":[52],"(RL)":[53],"agents":[54],"by":[55,83],"leveraging":[56],"the":[57,76,90],"task":[58,69,87],"compositionality.":[59],"Our":[60],"proposed":[61,116],"method":[62,117],"a":[64,105,126],"meta-RL":[65],"algorithm":[66],"with":[67],"disentangled":[68],"representation,":[70],"explicitly":[71],"encoding":[72],"aspects":[74],"tasks.":[77],"Policy":[78],"then":[81],"performed":[82],"inferring":[84],"unseen":[85,122],"representations":[88],"via":[89],"obtained":[91],"disentanglement":[92],"without":[93],"extra":[94],"exploration.":[95],"The":[96],"evaluation":[97],"conducted":[99],"on":[100],"three":[101],"simulated":[102],"challenging":[106],"real-world":[107],"robotic":[108],"insertion":[109],"task.":[110],"Experimental":[111],"results":[112],"demonstrate":[113],"that":[114],"our":[115],"achieves":[118],"in":[125],"manner.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}