{"id":"https://openalex.org/W4402354151","doi":"https://doi.org/10.15607/rss.2024.xx.125","title":"Learning to Learn Faster from Human Feedback with Language Model Predictive Control","display_name":"Learning to Learn Faster from Human Feedback with Language Model Predictive Control","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402354151","doi":"https://doi.org/10.15607/rss.2024.xx.125"},"language":"en","primary_location":{"id":"doi:10.15607/rss.2024.xx.125","doi":"https://doi.org/10.15607/rss.2024.xx.125","is_oa":false,"landing_page_url":"https://doi.org/10.15607/rss.2024.xx.125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XX","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.11450","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091443553","display_name":"Jacky Liang","orcid":"https://orcid.org/0009-0007-8969-0915","observed_orcids":["https://orcid.org/0009-0007-8969-0915"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jacky Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676785","display_name":"Fei Xia","orcid":"https://orcid.org/0000-0003-4343-1444","observed_orcids":["https://orcid.org/0000-0003-4343-1444","https://orcid.org/0000-0003-0793-3113"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015524477","display_name":"Wenhao Yu","orcid":"https://orcid.org/0000-0001-8263-8224","observed_orcids":["https://orcid.org/0000-0001-8263-8224","https://orcid.org/0000-0003-1521-2674"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005577303","display_name":"Andy Zeng","orcid":"https://orcid.org/0000-0002-4319-2159","observed_orcids":["https://orcid.org/0000-0002-4319-2159"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andy Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043566305","display_name":"Maria Attarian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Attarian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004820590","display_name":"Maria Bauz\u00e1","orcid":"https://orcid.org/0000-0002-8251-8019","observed_orcids":["https://orcid.org/0000-0002-8251-8019"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Villalonga","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058726487","display_name":"Matthew Bennice","orcid":"https://orcid.org/0009-0009-3294-4659","observed_orcids":["https://orcid.org/0009-0009-3294-4659"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthew Bennice","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043765267","display_name":"Alex Bewley","orcid":"https://orcid.org/0000-0002-8428-9264","observed_orcids":["https://orcid.org/0000-0002-8428-9264"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Bewley","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092031998","display_name":"Adil Dostmohamed","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adil Dostmohamed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069825251","display_name":"Chuyuan Fu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuyuan Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006600962","display_name":"Nimrod Gileadi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nimrod Gileadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042731148","display_name":"Marissa Giustina","orcid":"https://orcid.org/0000-0002-1283-2862","observed_orcids":["https://orcid.org/0000-0002-1283-2862"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marissa Giustina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025695094","display_name":"Keerthana Gopalakrishnan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keerthana Gopalakrishnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014567358","display_name":"Leonard Hasenclever","orcid":"https://orcid.org/0000-0003-1844-696X","observed_orcids":["https://orcid.org/0000-0003-1844-696X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leonard Hasenclever","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102771619","display_name":"Jan Humplik","orcid":"https://orcid.org/0000-0002-7573-7635","observed_orcids":["https://orcid.org/0000-0002-7573-7635"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Humplik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050024610","display_name":"Jasmine Hsu","orcid":"https://orcid.org/0000-0002-2342-8312","observed_orcids":["https://orcid.org/0000-0002-2342-8312"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jasmine Hsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Nikhil Joshi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikhil Joshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093973964","display_name":"Ben Jyenis","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Jyenis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015027910","display_name":"J. Chase Kew","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J Kew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036680156","display_name":"Sean Kirmani","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sean Kirmani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037275024","display_name":"Tsang-Wei Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsang-Wei Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030702181","display_name":"Kuang-Huei Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuang-Huei Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002552377","display_name":"Assaf Hurwitz Michaely","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Assaf Michaely","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108982318","display_name":"Joss Moore","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joss Moore","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033234426","display_name":"Kenneth Oslund","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenneth Oslund","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008638246","display_name":"Dushyant Rao","orcid":"https://orcid.org/0000-0002-1372-2884","observed_orcids":["https://orcid.org/0000-0002-1372-2884"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dushyant Rao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000576583","display_name":"Allen Z. Ren","orcid":"https://orcid.org/0000-0001-5306-2844","observed_orcids":["https://orcid.org/0000-0001-5306-2844"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Allen Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048215271","display_name":"Baruch Tabanpour","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baruch Tabanpour","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101445461","display_name":"Quan Vuong","orcid":"https://orcid.org/0009-0009-1829-9614","observed_orcids":["https://orcid.org/0009-0009-1829-9614"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan Vuong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051147070","display_name":"Ayzaan Wahid","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayzaan Wahid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025016495","display_name":"Ted G. Xiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ted Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755964","display_name":"Ying Xu","orcid":"https://orcid.org/0000-0002-2401-7718","observed_orcids":["https://orcid.org/0000-0002-2401-7718","https://orcid.org/0000-0003-0530-2123","https://orcid.org/0000-0003-0839-3892"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068788467","display_name":"Vincent Zhuang","orcid":"https://orcid.org/0009-0007-2931-3069","observed_orcids":["https://orcid.org/0009-0007-2931-3069"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Zhuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001599037","display_name":"Peng Xu","orcid":"https://orcid.org/0000-0003-4268-4976","observed_orcids":["https://orcid.org/0000-0003-4268-4976"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061223486","display_name":"Erik Frey","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erik Frey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068453232","display_name":"Ken Caluwaerts","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ken Caluwaerts","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086928709","display_name":"Tingnan Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tingnan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018507768","display_name":"Brian Ichter","orcid":"https://orcid.org/0000-0002-6955-6432","observed_orcids":["https://orcid.org/0000-0002-6955-6432"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Ichter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066924496","display_name":"Jonathan Tompson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Tompson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066958631","display_name":"Leila A. Takayama","orcid":"https://orcid.org/0000-0003-0790-6123","observed_orcids":["https://orcid.org/0000-0003-0790-6123"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leila Takayama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013813527","display_name":"Vincent Vanhoucke","orcid":"https://orcid.org/0000-0003-0544-2791","observed_orcids":["https://orcid.org/0000-0003-0544-2791"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Vanhoucke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025419994","display_name":"Izhak Shafran","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Izhak Shafran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010248533","display_name":"Maja J. Matari\u0107","orcid":"https://orcid.org/0000-0001-8958-6666","observed_orcids":["https://orcid.org/0000-0001-8958-6666"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maja Mataric","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080725225","display_name":"Dorsa Sadigh","orcid":"https://orcid.org/0000-0002-7802-9183","observed_orcids":["https://orcid.org/0000-0002-7802-9183"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dorsa Sadigh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062951341","display_name":"Nicolas Heess","orcid":"https://orcid.org/0000-0001-7876-9256","observed_orcids":["https://orcid.org/0000-0001-7876-9256"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Heess","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111514705","display_name":"Kanishka Rao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kanishka Rao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114129126","display_name":"Nik Stewart","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nik Stewart","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103241086","display_name":"Jie Tan","orcid":"https://orcid.org/0000-0002-7947-0333","observed_orcids":["https://orcid.org/0000-0002-7947-0333"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090570382","display_name":"Carolina Parada","orcid":"https://orcid.org/0009-0000-7772-4646","observed_orcids":["https://orcid.org/0009-0000-7772-4646"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carolina Parada","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.3463,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.98112825,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.951200008392334,"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":0.951200008392334,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.01600000075995922,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0038999998942017555,"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/human-feedback","display_name":"human feedback","score":0.9129999876022339},{"id":"https://openalex.org/keywords/learning-from-feedback","display_name":"learning from feedback","score":0.656000018119812},{"id":"https://openalex.org/keywords/reinforcement-learning-from-human-feedback","display_name":"reinforcement learning from human feedback","score":0.7170000076293945},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.550000011920929},{"id":"https://openalex.org/keywords/control-policy-learning","display_name":"control policy learning","score":0.382999986410141}],"concepts":[{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.701042115688324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6987449526786804},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.5317971110343933},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5011956691741943},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.471219927072525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4199894070625305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3739720582962036},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2325238287448883},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13457408547401428}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.15607/rss.2024.xx.125","doi":"https://doi.org/10.15607/rss.2024.xx.125","is_oa":false,"landing_page_url":"https://doi.org/10.15607/rss.2024.xx.125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XX","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.11450","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.11450","pdf_url":"https://arxiv.org/pdf/2402.11450","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,"listed_in":[],"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":"doi:10.48550/arxiv.2402.11450","doi":"https://doi.org/10.48550/arxiv.2402.11450","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.11450","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,"listed_in":[],"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:2402.11450","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.11450","pdf_url":"https://arxiv.org/pdf/2402.11450","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,"listed_in":[],"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":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402354151.pdf","grobid_xml":"https://content.openalex.org/works/W4402354151.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1990079087","https://openalex.org/W2101188133","https://openalex.org/W3202234113","https://openalex.org/W4248731570","https://openalex.org/W2381210024","https://openalex.org/W2060165215","https://openalex.org/W2384015130","https://openalex.org/W4285595274","https://openalex.org/W2556120871","https://openalex.org/W2052682608"],"abstract_inverted_index":{"Large":[0],"language":[1,20,139],"models":[2],"(LLMs)":[3],"have":[4],"been":[5],"shown":[6],"to":[7,25,37,50,89,103,153,178,182,187,199,231],"exhibit":[8],"a":[9,130,159,193],"wide":[10],"range":[11],"of":[12,69,110,216,226,245],"capabilities,":[13],"such":[14,172],"as":[15,60,62,129,173],"writing":[16],"robot":[17,27,86,144,208,252],"code":[18,145],"from":[19,229],"commands":[21],"--":[22,163,210],"enabling":[23],"non-experts":[24],"direct":[26],"behaviors,":[28],"modify":[29],"them":[30,36],"based":[31],"on":[32,203,250],"feedback,":[33],"or":[34],"compose":[35],"perform":[38],"new":[39,248],"tasks.":[40],"However,":[41],"these":[42],"capabilities":[43],"(driven":[44],"by":[45,107,219,256],"in-context":[46,92,246],"learning)":[47],"are":[48,127,141,147],"limited":[49],"short-term":[51],"interactions,":[52],"where":[53],"users'":[54],"feedback":[55],"remains":[56],"relevant":[57],"for":[58],"only":[59],"long":[61],"it":[63],"fits":[64],"within":[65],"the":[66,70,85,113,116,223,242],"context":[67],"size":[68],"LLM,":[71],"and":[72,94,143,254,261],"can":[73,165],"be":[74,166],"forgotten":[75],"over":[76],"longer":[77],"interactions.":[78],"In":[79],"this":[80],"work,":[81],"we":[82],"investigate":[83],"fine-tuning":[84],"code-writing":[87],"LLMs,":[88],"remember":[90],"their":[91,96],"interactions":[93,126,156],"improve":[95,200],"teachability":[97,202],"i.e.,":[98],"how":[99],"efficiently":[100],"they":[101],"adapt":[102],"human":[104,138,227],"inputs":[105,140],"(measured":[106],"average":[108,224],"number":[109,225],"corrections":[111,228],"before":[112],"user":[114],"considers":[115],"task":[117],"successful).":[118],"Our":[119],"key":[120],"observation":[121],"is":[122,157],"that":[123,164,195,235],"when":[124],"human-robot":[125],"viewed":[128],"partially":[131],"observable":[132],"Markov":[133],"decision":[134],"process":[135],"(in":[136],"which":[137],"observations,":[142],"outputs":[146],"actions),":[148],"then":[149],"training":[150,158],"an":[151],"LLM":[152],"complete":[154],"previous":[155],"transition":[160],"dynamics":[161],"model":[162,174],"combined":[167],"with":[168],"classic":[169],"robotics":[170],"techniques":[171],"predictive":[175],"control":[176],"(MPC)":[177],"discover":[179],"shorter":[180],"paths":[181],"success.":[183],"This":[184],"gives":[185],"rise":[186],"Language":[188],"Model":[189],"Predictive":[190],"Control":[191],"(LMPC),":[192],"framework":[194],"fine-tunes":[196],"PaLM":[197],"2":[198],"its":[201],"78":[204],"tasks":[205,218,249],"across":[206],"5":[207],"embodiments":[209,253],"improving":[211,241],"non-expert":[212],"teaching":[213],"success":[214,243],"rates":[215],"unseen":[217,251],"26.9%":[220],"while":[221],"reducing":[222],"2.4":[230],"1.9.":[232],"Experiments":[233],"show":[234],"LMPC":[236],"also":[237],"produces":[238],"strong":[239],"meta-learners,":[240],"rate":[244],"learning":[247],"APIs":[255],"31.5%.":[257],"See":[258],"videos,":[259],"code,":[260],"demos":[262],"at:":[263],"https://robot-teaching.github.io/.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2025-10-10T00:00:00"}
