{"id":"https://openalex.org/W4390905082","doi":"https://doi.org/10.1109/lra.2024.3354626","title":"StROL: Stabilized and Robust Online Learning From Humans","display_name":"StROL: Stabilized and Robust Online Learning From Humans","publication_year":2024,"publication_date":"2024-01-16","ids":{"openalex":"https://openalex.org/W4390905082","doi":"https://doi.org/10.1109/lra.2024.3354626"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3354626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3354626","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/A5014071264","display_name":"Shaunak A. Mehta","orcid":"https://orcid.org/0000-0002-3160-6879"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shaunak A. Mehta","raw_affiliation_strings":["Collaborative Robotics Lab (Collab), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Collaborative Robotics Lab (Collab), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705257","display_name":"Forrest Meng","orcid":"https://orcid.org/0009-0005-2056-4852"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Forrest Meng","raw_affiliation_strings":["Collaborative Robotics Lab (Collab), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Collaborative Robotics Lab (Collab), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050279893","display_name":"Andrea Bajcsy","orcid":"https://orcid.org/0000-0001-7969-9376"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Bajcsy","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063608480","display_name":"Dylan P. Losey","orcid":"https://orcid.org/0000-0002-8787-5293"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dylan P. Losey","raw_affiliation_strings":["Collaborative Robotics Lab (Collab), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Collaborative Robotics Lab (Collab), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014071264"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":1.4504,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83004302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"9","issue":"3","first_page":"2303","last_page":"2310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9966999888420105,"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":0.9966999888420105,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9778000116348267,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6751995086669922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6636325120925903},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.6264986991882324},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5822300910949707},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.5343405604362488},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5084666013717651},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.47607889771461487},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.46657595038414},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4664582312107086},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.41105523705482483},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.28709203004837036},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21434944868087769}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6751995086669922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6636325120925903},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6264986991882324},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5822300910949707},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.5343405604362488},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5084666013717651},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.47607889771461487},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.46657595038414},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4664582312107086},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.41105523705482483},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.28709203004837036},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21434944868087769},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3354626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3354626","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1837766154","https://openalex.org/W2003273395","https://openalex.org/W2141467654","https://openalex.org/W2169498096","https://openalex.org/W2329310016","https://openalex.org/W2799280697","https://openalex.org/W2907920236","https://openalex.org/W3003858867","https://openalex.org/W3011722025","https://openalex.org/W3035186145","https://openalex.org/W3040033967","https://openalex.org/W3091627088","https://openalex.org/W3092948749","https://openalex.org/W3098198982","https://openalex.org/W3103763075","https://openalex.org/W3106171760","https://openalex.org/W3128528928","https://openalex.org/W3133184250","https://openalex.org/W3134935089","https://openalex.org/W3135809806","https://openalex.org/W3206023142","https://openalex.org/W3207713159","https://openalex.org/W3208223622","https://openalex.org/W3216784117","https://openalex.org/W4323870803","https://openalex.org/W4386981938","https://openalex.org/W4389665836","https://openalex.org/W6785876034"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W3123835761","https://openalex.org/W3041944716"],"abstract_inverted_index":{"Robots":[0],"often":[1],"need":[2],"to":[3,45,94,99,117,136,163],"learn":[4,118],"the":[5,11,24,47,59,65,76,81,88,101,105,123,137,159,167],"human's":[6,25,60,82,138],"reward":[7,61,198],"function":[8],"online,":[9],"during":[10],"current":[12,31],"interaction.":[13],"This":[14,91],"real-time":[15],"learning":[16,21,55,67,107,120,125,131,153],"requires":[17],"fast":[18],"but":[19],"approximate":[20],"rules:":[22,121],"when":[23,57,166],"behavior":[26],"is":[27,161,169],"noisy":[28],"or":[29],"suboptimal,":[30],"approximations":[32],"can":[33,155],"result":[34],"in":[35,40,185],"unstable":[36],"robot":[37],"learning.":[38,199],"Accordingly,":[39],"this":[41],"letter":[42],"we":[43,180],"seek":[44],"enhance":[46],"robustness":[48],"and":[49,172,176,190],"convergence":[50],"properties":[51],"of":[52,145],"gradient":[53],"descent":[54],"rules":[56,154],"inferring":[58],"parameters.":[62],"We":[63],"model":[64],"robot's":[66,106],"algorithm":[68,112],"as":[69],"a":[70,129,142,177,186],"<italic":[71],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[72],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">dynamical":[73],"system</i>":[74],"over":[75],"human":[77,146,160,168],"preference":[78],"parameters,":[79],"where":[80],"true":[83,139],"(but":[84],"unknown)":[85],"preferences":[86],"are":[87],"equilibrium":[89],"point.":[90],"enables":[92],"us":[93],"perform":[95],"Lyapunov":[96],"stability":[97],"analysis":[98],"derive":[100],"conditions":[102,116],"under":[103,141],"which":[104],"dynamics":[108],"converge.":[109],"Our":[110],"proposed":[111],"(StROL)":[113],"uses":[114],"these":[115,150],"robust-by-design":[119],"given":[122],"original":[124],"dynamics,":[126],"StROL":[127,183],"outputs":[128],"modified":[130],"rule":[132],"that":[133,182],"now":[134],"converges":[135],"parameters":[140],"larger":[143],"set":[144],"inputs.":[147],"In":[148],"practice,":[149],"autonomously":[151],"generated":[152],"correctly":[156],"infer":[157],"what":[158],"trying":[162],"convey,":[164],"even":[165],"noisy,":[170],"biased,":[171],"suboptimal.":[173],"Across":[174],"simulations":[175],"user":[178],"study":[179],"find":[181],"results":[184],"more":[187],"accurate":[188],"estimate":[189],"less":[191],"regret":[192],"than":[193],"state-of-the-art":[194],"approaches":[195],"for":[196],"online":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}