{"id":"https://openalex.org/W4413945048","doi":"https://doi.org/10.1109/icra55743.2025.11127633","title":"Flora: Sample-Efficient Preference-Based Rl Via Low-Rank Style Adaptation of Reward Functions","display_name":"Flora: Sample-Efficient Preference-Based Rl Via Low-Rank Style Adaptation of Reward Functions","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413945048","doi":"https://doi.org/10.1109/icra55743.2025.11127633"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127633","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/A5084998580","display_name":"Daniel Marta","orcid":"https://orcid.org/0000-0002-3510-5481"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Daniel Marta","raw_affiliation_strings":["KTH Royal Institute of Technology,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056430836","display_name":"Simon Holk","orcid":"https://orcid.org/0000-0001-5727-8140"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Simon Holk","raw_affiliation_strings":["KTH Royal Institute of Technology,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063841377","display_name":"Miguel Vasco","orcid":"https://orcid.org/0000-0002-5761-4105"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Miguel Vasco","raw_affiliation_strings":["KTH Royal Institute of Technology,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064860545","display_name":"Jens Lundell","orcid":"https://orcid.org/0000-0003-2296-6685"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jens Lundell","raw_affiliation_strings":["KTH Royal Institute of Technology,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048949232","display_name":"Timon Homberger","orcid":"https://orcid.org/0009-0000-4369-1110"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Timon Homberger","raw_affiliation_strings":["KTH Royal Institute of Technology,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013137247","display_name":"Finn Lukas Busch","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Finn Busch","raw_affiliation_strings":["KTH Royal Institute of Technology,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014501729","display_name":"Olov Andersson","orcid":"https://orcid.org/0000-0001-7248-1112"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Olov Andersson","raw_affiliation_strings":["KTH Royal Institute of Technology,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074819656","display_name":"Danica Kragic","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Danica Kragic","raw_affiliation_strings":["KTH Royal Institute of Technology,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082559019","display_name":"Iolanda Leite","orcid":"https://orcid.org/0000-0002-2212-4325"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Iolanda Leite","raw_affiliation_strings":["KTH Royal Institute of Technology,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5084998580"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":3.392,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92990799,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4789","last_page":"4796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10487","display_name":"Plant and animal studies","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1105","display_name":"Ecology, Evolution, Behavior and Systematics"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10487","display_name":"Plant and animal studies","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1105","display_name":"Ecology, Evolution, Behavior and Systematics"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7503645420074463},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7422887086868286},{"id":"https://openalex.org/keywords/flora","display_name":"Flora (microbiology)","score":0.7134473919868469},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6939594745635986},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6805285215377808},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5658060312271118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48274654150009155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3725578188896179},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2850140333175659},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25794535875320435},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.25237542390823364},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.20281100273132324},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1980961263179779},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.14844653010368347},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08775678277015686},{"id":"https://openalex.org/keywords/paleontology","display_name":"Paleontology","score":0.06544068455696106},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06362995505332947}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7503645420074463},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7422887086868286},{"id":"https://openalex.org/C2777234453","wikidata":"https://www.wikidata.org/wiki/Q2033092","display_name":"Flora (microbiology)","level":3,"score":0.7134473919868469},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6939594745635986},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6805285215377808},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5658060312271118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48274654150009155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3725578188896179},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2850140333175659},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25794535875320435},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25237542390823364},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.20281100273132324},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1980961263179779},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.14844653010368347},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08775678277015686},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.06544068455696106},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06362995505332947},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127633","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":8,"referenced_works":["https://openalex.org/W2763110165","https://openalex.org/W2962770929","https://openalex.org/W3036619998","https://openalex.org/W3177323791","https://openalex.org/W4319318414","https://openalex.org/W4367016688","https://openalex.org/W4392182482","https://openalex.org/W4402951578"],"related_works":["https://openalex.org/W2366061989","https://openalex.org/W2129686347","https://openalex.org/W2979501248","https://openalex.org/W2389706699","https://openalex.org/W2358142510","https://openalex.org/W2137588987","https://openalex.org/W2978625163","https://openalex.org/W2386350532","https://openalex.org/W3112278740","https://openalex.org/W2048009886"],"abstract_inverted_index":{"Preference-based":[0],"reinforcement":[1],"learning":[2],"(PbRL)":[3],"is":[4,42],"a":[5,109],"suitable":[6],"approach":[7],"for":[8,36,117],"style":[9],"adaptation":[10,38,53,68],"of":[11,54,112,150],"pre-trained":[12,55],"robotic":[13,133,145],"behavior:":[14],"adapting":[15],"the":[16,30,37,52,58,77,83,87,94,104,119],"robot's":[17],"policy":[18],"to":[19,28,82,89,92,102,135],"follow":[20],"human":[21,136],"user":[22],"preferences":[23,35,137],"while":[24],"still":[25],"being":[26],"able":[27],"perform":[29,93],"original":[31,95,105],"task.":[32,96],"However,":[33],"collecting":[34],"process":[39],"in":[40,57,64],"robotics":[41],"often":[43],"challenging":[44],"and":[45,130,142,153],"time-consuming.":[46],"In":[47],"this":[48,65],"work":[49],"we":[50,100],"explore":[51],"robots":[56],"low-preference-data":[59],"regime.":[60],"We":[61,147],"show":[62],"that,":[63],"regime,":[66],"recent":[67],"approaches":[69],"suffer":[70],"from":[71],"catastrophic":[72],"reward":[73,79,106],"forgetting":[74],"(CRF),":[75],"where":[76],"updated":[78],"model":[80,107],"overfits":[81],"new":[84],"preferences,":[85],"leading":[86],"agent":[88],"become":[90],"unable":[91],"To":[97],"mitigate":[98],"CRF,":[99],"propose":[101],"enhance":[103],"with":[108],"small":[110],"number":[111],"parameters":[113],"(low-rank":[114],"matrices)":[115],"responsible":[116],"modeling":[118],"preference":[120],"adaptation.":[121],"Our":[122],"evaluation":[123],"shows":[124],"that":[125],"our":[126,151],"method":[127],"can":[128],"efficiently":[129],"effectively":[131],"adjust":[132],"behavior":[134],"across":[138],"simulation":[139],"benchmark":[140],"tasks":[141],"multiple":[143],"real-world":[144],"tasks.":[146],"provide":[148],"videos":[149],"results":[152],"source":[154],"code":[155],"at":[156],"https://sites.google.com/view/preflora/.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}