{"id":"https://openalex.org/W4406415458","doi":"https://doi.org/10.1109/lra.2025.3528663","title":"PrefCLM: Enhancing Preference-Based Reinforcement Learning With Crowdsourced Large Language Models","display_name":"PrefCLM: Enhancing Preference-Based Reinforcement Learning With Crowdsourced Large Language Models","publication_year":2025,"publication_date":"2025-01-15","ids":{"openalex":"https://openalex.org/W4406415458","doi":"https://doi.org/10.1109/lra.2025.3528663"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3528663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3528663","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/A5023498177","display_name":"Ruiqi Wang","orcid":"https://orcid.org/0000-0002-4323-8989"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruiqi Wang","raw_affiliation_strings":["Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-4323-8989","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101254875","display_name":"Dezhong Zhao","orcid":"https://orcid.org/0000-0003-4478-9595"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dezhong Zhao","raw_affiliation_strings":["Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0003-4478-9595","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109746539","display_name":"Ziqin Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziqin Yuan","raw_affiliation_strings":["Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0009-0005-8088-3636","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092103161","display_name":"Ike Obi","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ike Obi","raw_affiliation_strings":["Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-3910-8890","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076467173","display_name":"Byung\u2010Cheol Min","orcid":"https://orcid.org/0000-0001-6458-4365"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byung-Cheol Min","raw_affiliation_strings":["Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-6458-4365","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology, SMART Laboratory, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":14.8573,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.98640768,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"10","issue":"3","first_page":"2486","last_page":"2493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9933000206947327,"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":0.9933000206947327,"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/T12031","display_name":"Speech and dialogue systems","score":0.9858999848365784,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.982699990272522,"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/preference","display_name":"Preference","score":0.6453167796134949},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5734127163887024},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.47487470507621765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46256953477859497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3189888000488281},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.29545164108276367},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07799988985061646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06468817591667175}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6453167796134949},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5734127163887024},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47487470507621765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46256953477859497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3189888000488281},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29545164108276367},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07799988985061646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06468817591667175},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3528663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3528663","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":33,"referenced_works":["https://openalex.org/W2781585732","https://openalex.org/W2964397271","https://openalex.org/W3091243689","https://openalex.org/W3195851848","https://openalex.org/W4251598436","https://openalex.org/W4288327876","https://openalex.org/W4312480554","https://openalex.org/W4312550960","https://openalex.org/W4383108457","https://openalex.org/W4389667233","https://openalex.org/W4391157361","https://openalex.org/W4391855070","https://openalex.org/W4403752403","https://openalex.org/W4403780072","https://openalex.org/W6739585900","https://openalex.org/W6743368274","https://openalex.org/W6747387971","https://openalex.org/W6764045775","https://openalex.org/W6769596995","https://openalex.org/W6771179988","https://openalex.org/W6796168157","https://openalex.org/W6799431981","https://openalex.org/W6810044100","https://openalex.org/W6810339684","https://openalex.org/W6850848496","https://openalex.org/W6855192825","https://openalex.org/W6855797017","https://openalex.org/W6857151620","https://openalex.org/W6860364947","https://openalex.org/W6860855263","https://openalex.org/W6870532237","https://openalex.org/W6873607966","https://openalex.org/W6873856957"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Preference-based":[0],"reinforcement":[1],"learning":[2],"(PbRL)":[3],"is":[4],"emerging":[5],"as":[6,48],"a":[7,38,80],"promising":[8],"approach":[9],"to":[10,57,90,97,116,140,144],"teaching":[11],"robots":[12],"through":[13],"human":[14,26],"comparative":[15],"feedback":[16,27],"without":[17],"complex":[18],"reward":[19],"engineering.":[20],"However,":[21],"the":[22,67,91],"substantial":[23],"volume":[24],"of":[25],"required":[28],"hinders":[29],"broader":[30],"applications.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"introduce":[36,79],"PrefCLM,":[37],"novel":[39],"framework":[40],"that":[41,88,110],"utilizes":[42],"crowdsourced":[43],"large":[44],"language":[45],"models":[46],"(LLMs)":[47],"synthetic":[49],"teachers":[50,119],"in":[51,122,151],"PbRL.":[52],"We":[53,77],"utilize":[54],"Dempster-Shafer":[55],"Theory":[56],"fuse":[58],"individual":[59,145],"preference":[60],"beliefs":[61],"from":[62],"multiple":[63],"LLM":[64],"agents":[65],"at":[66],"score":[68],"level,":[69],"efficiently":[70],"leveraging":[71],"their":[72],"diversity":[73],"and":[74,85,93,120,126],"collective":[75,86],"intelligence.":[76],"also":[78],"human-in-the-loop":[81],"pipeline,":[82],"enabling":[83],"iterative":[84],"refinements":[87],"adapt":[89],"nuanced":[92],"individualized":[94],"preferences":[95],"inherent":[96],"human-robot":[98],"interaction":[99],"(HRI)":[100],"scenarios.":[101,153],"Experimental":[102],"results":[103],"across":[104],"various":[105],"general":[106],"RL":[107],"tasks":[108],"show":[109],"PrefCLM":[111],"achieves":[112],"competitive":[113],"performance":[114],"compared":[115],"expert-engineered":[117],"scripted":[118],"excels":[121],"facilitating":[123],"more":[124],"natural":[125],"efficient":[127],"behaviors.":[128],"A":[129],"real-world":[130],"user":[131,146,149],"study":[132],"(N":[133],"=":[134],"10)":[135],"further":[136],"demonstrates":[137],"its":[138],"capability":[139],"tailor":[141],"robot":[142],"behaviors":[143],"preferences,":[147],"enhancing":[148],"satisfaction":[150],"HRI":[152]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}