{"id":"https://openalex.org/W4416750180","doi":"https://doi.org/10.1109/iros60139.2025.11247163","title":"CueLearner: Bootstrapping and local policy adaptation from relative feedback","display_name":"CueLearner: Bootstrapping and local policy adaptation from relative feedback","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750180","doi":"https://doi.org/10.1109/iros60139.2025.11247163"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055851873","display_name":"Giulio Schiavi","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Giulio Schiavi","raw_affiliation_strings":["ETH Zurich,Autonomous Systems Lab,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Autonomous Systems Lab,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048141350","display_name":"Andrei Cramariuc","orcid":"https://orcid.org/0000-0002-9301-0253"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andrei Cramariuc","raw_affiliation_strings":["ETH Zurich,Robotics Systems Lab,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Robotics Systems Lab,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033725695","display_name":"Lionel Ott","orcid":"https://orcid.org/0000-0001-6554-0575"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lionel Ott","raw_affiliation_strings":["ETH Zurich,Autonomous Systems Lab,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Autonomous Systems Lab,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083003222","display_name":"Roland Siegwart","orcid":"https://orcid.org/0000-0002-2760-7983"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Roland Siegwart","raw_affiliation_strings":["ETH Zurich,Autonomous Systems Lab,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Autonomous Systems Lab,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7917","last_page":"7924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.18070000410079956,"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":0.18070000410079956,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.16930000483989716,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.0778999999165535,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.7706999778747559},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5964000225067139},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.43560001254081726},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4334000051021576},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.41100001335144043},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.3418999910354614}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7706999778747559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6660000085830688},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5964000225067139},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44369998574256897},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.41100001335144043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3903999924659729},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":12,"referenced_works":["https://openalex.org/W2128990851","https://openalex.org/W2156869222","https://openalex.org/W2788862220","https://openalex.org/W2795786572","https://openalex.org/W2799745602","https://openalex.org/W2963411833","https://openalex.org/W3001507548","https://openalex.org/W4214717370","https://openalex.org/W4250058668","https://openalex.org/W4313952519","https://openalex.org/W4367016688","https://openalex.org/W4402354098"],"related_works":[],"abstract_inverted_index":{"Human":[0],"guidance":[1,17],"has":[2,73],"emerged":[3],"as":[4,19,57],"a":[5,63,105,152,174,178],"powerful":[6],"tool":[7],"for":[8],"enhancing":[9],"reinforcement":[10,118,139],"learning":[11,140],"(RL).":[12],"However,":[13,86],"conventional":[14],"forms":[15,40],"of":[16,38,41,138],"such":[18,56],"demonstrations":[20],"or":[21,30,159],"binary":[22],"scalar":[23],"feedback":[24,47,49,77,98,112],"can":[25,78,130,150],"be":[26,79,131],"challenging":[27],"to":[28,52,59,81,92,108,133,154,172],"collect":[29],"have":[31,89],"low":[32],"information":[33,69],"content,":[34],"motivating":[35],"the":[36,60,135,157,160],"exploration":[37,144],"other":[39],"human":[42],"input.":[43],"Among":[44],"these,":[45],"relative":[46,76,111],"(i.e.,":[48],"on":[50,122],"how":[51],"improve":[53,134],"an":[54],"action,":[55],"\"more":[58],"left\")":[61],"offers":[62],"good":[64],"balance":[65],"between":[66],"usability":[67],"and":[68,96,113],"richness.":[70],"Previous":[71],"research":[72],"shown":[74],"that":[75],"used":[80,132],"enhance":[82],"policy":[83,94,153,176],"search":[84],"methods.":[85],"these":[87],"efforts":[88],"been":[90],"limited":[91],"specific":[93],"classes":[95],"use":[97],"inefficiently.":[99],"In":[100],"this":[101],"work,":[102],"we":[103,126,147,164],"introduce":[104],"novel":[106],"method":[107,129],"learn":[109,173],"from":[110],"combine":[114],"it":[115,149],"with":[116],"off-policy":[117],"learning.":[119],"Through":[120],"evaluations":[121],"two":[123],"sparse-reward":[124],"tasks,":[125],"demonstrate":[127,165],"our":[128,170],"sample":[136],"efficiency":[137],"by":[141,168],"guiding":[142],"its":[143],"process.":[145],"Additionally,":[146],"show":[148],"adapt":[151],"changes":[155],"in":[156,177],"environment":[158],"user\u2019s":[161],"preferences.":[162],"Finally,":[163],"real-world":[166],"applicability":[167],"employing":[169],"approach":[171],"navigation":[175],"sparse":[179],"reward":[180],"setting.":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}