{"id":"https://openalex.org/W3126833157","doi":"https://doi.org/10.1109/lra.2021.3057050","title":"Transfer Reinforcement Learning Across Homotopy Classes","display_name":"Transfer Reinforcement Learning Across Homotopy Classes","publication_year":2021,"publication_date":"2021-02-03","ids":{"openalex":"https://openalex.org/W3126833157","doi":"https://doi.org/10.1109/lra.2021.3057050","mag":"3126833157"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3057050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3057050","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5010800424","display_name":"Zhangjie Cao","orcid":"https://orcid.org/0000-0001-5098-2194"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhangjie Cao","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5098-2194","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043538173","display_name":"Minae Kwon","orcid":"https://orcid.org/0000-0002-3116-330X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minae Kwon","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3116-330X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080725225","display_name":"Dorsa Sadigh","orcid":"https://orcid.org/0000-0002-7802-9183"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dorsa Sadigh","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010800424"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.9598,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88293655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"6","issue":"2","first_page":"2706","last_page":"2713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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":0.9866999983787537,"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":0.8293321132659912},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6845762729644775},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6031386256217957},{"id":"https://openalex.org/keywords/homotopy","display_name":"Homotopy","score":0.5969277024269104},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5790773034095764},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4962840676307678},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.493373304605484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4747196435928345},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45619139075279236},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.4513189494609833},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4152054190635681},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39562708139419556},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2202446460723877},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1508350968360901}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8293321132659912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6845762729644775},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6031386256217957},{"id":"https://openalex.org/C5961521","wikidata":"https://www.wikidata.org/wiki/Q746083","display_name":"Homotopy","level":2,"score":0.5969277024269104},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5790773034095764},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4962840676307678},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.493373304605484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4747196435928345},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45619139075279236},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4513189494609833},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4152054190635681},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39562708139419556},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2202446460723877},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1508350968360901},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2021.3057050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3057050","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G3533906344","display_name":null,"funder_award_id":"2006388","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1840625103","https://openalex.org/W1968962398","https://openalex.org/W1969074599","https://openalex.org/W1977655452","https://openalex.org/W1992787855","https://openalex.org/W2095671661","https://openalex.org/W2097381042","https://openalex.org/W2100495367","https://openalex.org/W2108598243","https://openalex.org/W2118382603","https://openalex.org/W2144446635","https://openalex.org/W2149933564","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2186489521","https://openalex.org/W2201912979","https://openalex.org/W2426267443","https://openalex.org/W2427917354","https://openalex.org/W2440926996","https://openalex.org/W2578206533","https://openalex.org/W2583993537","https://openalex.org/W2604763608","https://openalex.org/W2624871570","https://openalex.org/W2726367589","https://openalex.org/W2726717203","https://openalex.org/W2735995851","https://openalex.org/W2786462443","https://openalex.org/W2788904251","https://openalex.org/W2789008106","https://openalex.org/W2823112946","https://openalex.org/W2886380958","https://openalex.org/W2952267586","https://openalex.org/W2962717849","https://openalex.org/W2962867954","https://openalex.org/W2962887844","https://openalex.org/W2962974944","https://openalex.org/W2963025296","https://openalex.org/W2963199420","https://openalex.org/W2963276406","https://openalex.org/W2963634205","https://openalex.org/W2963680188","https://openalex.org/W2963958573","https://openalex.org/W2964161785","https://openalex.org/W2964186069","https://openalex.org/W2964342357","https://openalex.org/W2971339032","https://openalex.org/W3017409624","https://openalex.org/W3028676366","https://openalex.org/W3047403664","https://openalex.org/W3091243689","https://openalex.org/W3100944043","https://openalex.org/W3103182070","https://openalex.org/W3104013016","https://openalex.org/W3110701971","https://openalex.org/W4200523064","https://openalex.org/W4214717370","https://openalex.org/W4256431479","https://openalex.org/W4293872189","https://openalex.org/W4295719664","https://openalex.org/W4297789758","https://openalex.org/W4298857966","https://openalex.org/W4299518610","https://openalex.org/W4300971732","https://openalex.org/W4319988532","https://openalex.org/W6637967152","https://openalex.org/W6674600207","https://openalex.org/W6682132143","https://openalex.org/W6682849425","https://openalex.org/W6687011383","https://openalex.org/W6717915398","https://openalex.org/W6718190810","https://openalex.org/W6729433768","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6739365718","https://openalex.org/W6740472315","https://openalex.org/W6740879895","https://openalex.org/W6745935785","https://openalex.org/W6748599296","https://openalex.org/W6748600884","https://openalex.org/W6753060773","https://openalex.org/W6753766000","https://openalex.org/W6756463683","https://openalex.org/W6756840741","https://openalex.org/W6767101815","https://openalex.org/W6769609827","https://openalex.org/W6776458826","https://openalex.org/W6780559895","https://openalex.org/W6787002401","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W154868527","https://openalex.org/W1494268238","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W1976468483","https://openalex.org/W1516574938","https://openalex.org/W2563912921","https://openalex.org/W2407611282"],"abstract_inverted_index":{"The":[0],"ability":[1],"for":[2,18],"robots":[3],"to":[4,9,103,140,173],"transfer":[5,32,61,142],"their":[6,69],"learned":[7],"knowledge":[8],"new":[10],"tasks-where":[11],"data":[12],"is":[13,41,119],"scarce-is":[14],"a":[15,28,106,123,132,136,169],"fundamental":[16],"challenge":[17],"successful":[19],"robot":[20],"learning.":[21,50],"While":[22],"fine-tuning":[23,59,79,96,104,125,163],"has":[24],"been":[25],"well-studied":[26],"as":[27,43],"simple":[29],"but":[30],"effective":[31],"approach":[33,151],"in":[34,45,60,116,168],"the":[35,46,56,113,161],"context":[36,47],"of":[37,48,58,89,131],"supervised":[38],"learning,":[39],"it":[40],"not":[42],"well-explored":[44],"reinforcement":[49,62],"In":[51],"this":[52],"work,":[53],"we":[54,148],"study":[55],"problem":[57],"learning":[63,138,143],"when":[64,82],"tasks":[65],"are":[66,73,87],"parameterized":[67],"by":[68],"reward":[70],"functions,":[71],"which":[72],"known":[74],"beforehand.":[75],"We":[76,93,121],"conjecture":[77],"that":[78,95,129,160],"drastically":[80],"underperforms":[81],"source":[83],"and":[84,115,135,157],"target":[85],"trajectories":[86],"part":[88],"different":[90],"homotopy":[91,100,107,145],"classes:":[92],"demonstrate":[94],"policy":[97],"parameters":[98],"across":[99,144],"classes":[101],"compared":[102,172],"within":[105],"class":[108],"requires":[109],"more":[110],"interaction":[111],"with":[112],"environment,":[114],"certain":[117],"cases":[118],"impossible.":[120],"propose":[122],"novel":[124],"algorithm,":[126],"Ease-In-Ease-Out":[127,162],"fine-tuning,":[128],"consists":[130],"relaxing":[133],"stage":[134,139],"curriculum":[137],"enable":[141],"classes.":[146],"Finally,":[147],"evaluate":[149],"our":[150],"on":[152],"several":[153],"robotics-inspired":[154],"simulated":[155],"environments":[156],"empirically":[158],"verify":[159],"method":[164],"can":[165],"successfully":[166],"fine-tune":[167],"sample-efficient":[170],"way":[171],"existing":[174],"baselines.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}