{"id":"https://openalex.org/W4410636344","doi":"https://doi.org/10.1145/3701716.3717570","title":"Adaptive Confidence-aware Preference-based Reinforcement Learning with Noisy Feedback","display_name":"Adaptive Confidence-aware Preference-based Reinforcement Learning with Noisy Feedback","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636344","doi":"https://doi.org/10.1145/3701716.3717570"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3717570","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717570","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717570","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717570","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuhao Gong","orcid":"https://orcid.org/0009-0001-1146-9715"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Gong","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0001-1146-9715","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017984888","display_name":"Zhenbo Lu","orcid":"https://orcid.org/0000-0002-0918-7524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenbo Lu","raw_affiliation_strings":["Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0918-7524","affiliations":[{"raw_affiliation_string":"Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026001351","display_name":"Wanxuan Lu","orcid":"https://orcid.org/0000-0003-4612-508X"},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanxuan Lu","raw_affiliation_strings":["Aerospace Information Research Institute, CAS, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4612-508X","affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1690-9836","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2188-3028","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2120","last_page":"2128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9857000112533569,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8036808967590332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7277188897132874},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7070431113243103},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5196586847305298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4480135142803192},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3890116810798645},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14894896745681763},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11694568395614624},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09777745604515076}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8036808967590332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7277188897132874},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7070431113243103},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5196586847305298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4480135142803192},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3890116810798645},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14894896745681763},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11694568395614624},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09777745604515076},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3717570","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717570","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717570","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3717570","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717570","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717570","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636344.pdf","grobid_xml":"https://content.openalex.org/works/W4410636344.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W1583837637","https://openalex.org/W2145339207","https://openalex.org/W2763110165","https://openalex.org/W2990138404","https://openalex.org/W3156669901","https://openalex.org/W3196904728","https://openalex.org/W4225766285","https://openalex.org/W4319653664","https://openalex.org/W4367046801","https://openalex.org/W4367047188","https://openalex.org/W4367047203","https://openalex.org/W4367047348","https://openalex.org/W4396723147","https://openalex.org/W4396723154","https://openalex.org/W4396736348","https://openalex.org/W4396757501","https://openalex.org/W4396758667","https://openalex.org/W4396758734","https://openalex.org/W6600302053"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"As":[0],"AI":[1],"systems":[2],"become":[3],"more":[4],"integrated":[5],"into":[6],"society,":[7],"ensuring":[8],"they":[9],"align":[10],"with":[11,73],"human":[12,28],"values":[13],"and":[14,94,106,127],"exhibit":[15],"responsible":[16],"behavior":[17],"is":[18,53],"crucial.":[19],"Preference-based":[20],"Reinforcement":[21],"Learning":[22],"(PbRL),":[23],"which":[24],"learns":[25],"directly":[26],"from":[27],"feedback,":[29,49],"offers":[30],"a":[31,64,80,129],"promising":[32],"approach":[33,78],"to":[34,44,55,66,99,114,119],"achieving":[35],"this":[36],"alignment.":[37],"However,":[38],"PbRL":[39,71,154],"faces":[40],"significant":[41],"challenges":[42],"related":[43],"data":[45,87,105,125],"quality,":[46],"like":[47],"inconsistent":[48],"especially":[50],"when":[51],"crowdsourcing":[52],"used":[54],"collect":[56],"feedback.":[57],"To":[58],"address":[59],"these":[60],"issues,":[61],"we":[62],"propose":[63],"method":[65],"enhance":[67],"the":[68,101,116,121,135,142,150],"robustness":[69],"of":[70,103,124,137,152],"algorithms":[72,155],"noisy":[74,85,104],"preference":[75],"data.":[76],"Our":[77],"provides":[79],"standardized":[81],"framework":[82],"for":[83],"handling":[84],"feedback":[86],"by":[88],"incorporating":[89],"confidence":[90],"analysis,":[91],"temporal":[92],"smoothing,":[93],"an":[95],"adaptive":[96],"penalty":[97],"mechanism":[98],"reduce":[100],"impact":[102],"improve":[107],"learning":[108,131],"stability.":[109],"These":[110],"techniques":[111],"work":[112],"synergistically":[113],"ensure":[115],"algorithm's":[117],"ability":[118],"mitigate":[120],"negative":[122],"effects":[123],"imperfections":[126],"maintain":[128],"stable":[130],"trajectory.":[132],"We":[133],"demonstrate":[134],"effectiveness":[136],"our":[138],"approach,":[139],"CA-PbRL,":[140],"in":[141,164],"Meta-World":[143],"environment,":[144],"showing":[145],"that":[146],"it":[147],"can":[148],"recover":[149],"performance":[151],"existing":[153],"under":[156],"various":[157],"noise":[158],"conditions,":[159],"thereby":[160],"facilitating":[161],"their":[162],"application":[163],"real-world":[165],"environments.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}