{"id":"https://openalex.org/W4413925998","doi":"https://doi.org/10.1109/icra55743.2025.11128278","title":"TREND: Tri-Teaching for Robust Preference-based Reinforcement Learning with Demonstrations","display_name":"TREND: Tri-Teaching for Robust Preference-based Reinforcement Learning with Demonstrations","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925998","doi":"https://doi.org/10.1109/icra55743.2025.11128278"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5064995424","display_name":"Shuaiyi Huang","orcid":"https://orcid.org/0000-0003-0555-2077"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shuaiyi Huang","raw_affiliation_strings":["University of Maryland,College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050886880","display_name":"Mara Levy","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mara Levy","raw_affiliation_strings":["University of Maryland,College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027792828","display_name":"Anubhav Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anubhav Gupta","raw_affiliation_strings":["University of Maryland,College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114730065","display_name":"Daniel Ekpo","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Ekpo","raw_affiliation_strings":["University of Maryland,College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013554787","display_name":"Ruijie Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruijie Zheng","raw_affiliation_strings":["University of Maryland,College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101614443","display_name":"Abhinav Shrivastava","orcid":"https://orcid.org/0000-0001-8928-8554"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Shrivastava","raw_affiliation_strings":["University of Maryland,College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5064995424"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13470841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9574","last_page":"9581"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9375,"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":0.9375,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.9352999925613403,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.923799991607666,"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":0.7146760821342468},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6589918732643127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6173384785652161},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4208259880542755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38973885774612427},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17761030793190002},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11226588487625122},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10339391231536865},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05504247546195984}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7146760821342468},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6589918732643127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6173384785652161},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4208259880542755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38973885774612427},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17761030793190002},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11226588487625122},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10339391231536865},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05504247546195984}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2089943482","https://openalex.org/W2098584016","https://openalex.org/W2573393487","https://openalex.org/W2735318784","https://openalex.org/W2763110165","https://openalex.org/W2962933067","https://openalex.org/W2982121679","https://openalex.org/W3033630125","https://openalex.org/W3039563104","https://openalex.org/W3042609801","https://openalex.org/W3094963793","https://openalex.org/W4287947470","https://openalex.org/W4312400547","https://openalex.org/W4386071704","https://openalex.org/W4390873547","https://openalex.org/W4391888649","https://openalex.org/W4401024730","https://openalex.org/W4401414398","https://openalex.org/W4402916973","https://openalex.org/W4402917031","https://openalex.org/W4404781949","https://openalex.org/W4405785406","https://openalex.org/W4413925490"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Preference":[0],"feedback":[1],"collected":[2],"by":[3],"human":[4],"or":[5],"VLM":[6],"annotators":[7],"is":[8],"often":[9],"noisy,":[10],"presenting":[11],"a":[12,32,41],"significant":[13],"challenge":[14],"for":[15,44,75],"preference-based":[16],"reinforcement":[17],"learning":[18],"that":[19,35],"relies":[20],"on":[21,98],"accurate":[22],"preference":[23,61,124],"labels.":[24],"To":[25],"address":[26],"this":[27],"challenge,":[28],"we":[29],"propose":[30],"TREND,":[31],"novel":[33],"framework":[34],"integrates":[36],"few-shot":[37],"expert":[38,89],"demonstrations":[39,90],"with":[40,110],"tri-teaching":[42],"strategy":[43],"effective":[45,119],"noise":[46,111],"mitigation.":[47],"Our":[48],"method":[49],"trains":[50],"three":[51,88],"reward":[52],"models":[53],"simultaneously,":[54],"where":[55],"each":[56],"model":[57],"views":[58],"its":[59,72,118],"small-loss":[60],"pairs":[62,70],"as":[63,83,85,113,115],"useful":[64,69],"knowledge":[65],"and":[66],"teaches":[67],"such":[68],"to":[71,87,91,105],"peer":[73],"network":[74],"updating":[76],"the":[77],"parameters.":[78],"Remarkably,":[79],"our":[80],"approach":[81],"requires":[82],"few":[84],"one":[86],"achieve":[92],"high":[93,114],"performance.":[94],"We":[95],"evaluate":[96],"TREND":[97],"various":[99],"robotic":[100],"manipulation":[101],"tasks,":[102],"achieving":[103],"up":[104],"90%":[106],"success":[107],"rates":[108],"even":[109],"levels":[112],"40%,":[116],"highlighting":[117],"robustness":[120],"in":[121],"handling":[122],"noisy":[123],"feedback.":[125]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}