{"id":"https://openalex.org/W4413918518","doi":"https://doi.org/10.1109/icra55743.2025.11127694","title":"Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences","display_name":"Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413918518","doi":"https://doi.org/10.1109/icra55743.2025.11127694"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127694","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":"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/A5101591226","display_name":"Ziang Liu","orcid":"https://orcid.org/0009-0007-5488-1156"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziang Liu","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100929170","display_name":"Junjie Xu","orcid":"https://orcid.org/0000-0002-3673-786X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Xu","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043728985","display_name":"Xingjiao Wu","orcid":"https://orcid.org/0000-0001-9146-051X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjiao Wu","raw_affiliation_strings":["School of Pharmacy, East China Normal University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Pharmacy, East China Normal University,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001284747","display_name":"Jing Yang","orcid":"https://orcid.org/0000-0003-3724-6066"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102023120","display_name":"He Liang","orcid":"https://orcid.org/0000-0002-5600-1286"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1163","last_page":"1169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10050","display_name":"Multi-Criteria Decision Making","score":0.32120001316070557,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10050","display_name":"Multi-Criteria Decision Making","score":0.32120001316070557,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.8337832093238831},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.7678260803222656},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6465885639190674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5185937881469727},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5016210079193115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4714568257331848},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35283327102661133},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24385955929756165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2394610047340393},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1865888237953186},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.171564519405365}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.8337832093238831},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.7678260803222656},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6465885639190674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5185937881469727},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5016210079193115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4714568257331848},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35283327102661133},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24385955929756165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2394610047340393},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1865888237953186},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.171564519405365}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127694","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":[{"id":"https://openalex.org/G7365027386","display_name":null,"funder_award_id":"24511104000","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G7742197465","display_name":null,"funder_award_id":"2022ZD0161800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2045031658","https://openalex.org/W2109910161","https://openalex.org/W2962759351","https://openalex.org/W2963544079","https://openalex.org/W3141797743","https://openalex.org/W3197594072","https://openalex.org/W4213377513","https://openalex.org/W4294875307","https://openalex.org/W4297964528","https://openalex.org/W4313837520","https://openalex.org/W4323022392","https://openalex.org/W4382239700","https://openalex.org/W4386285856","https://openalex.org/W4389667165","https://openalex.org/W4391399751","https://openalex.org/W4391967369","https://openalex.org/W4393147692","https://openalex.org/W4393148062"],"related_works":["https://openalex.org/W2937325523","https://openalex.org/W4403346496","https://openalex.org/W2954428433","https://openalex.org/W257970033","https://openalex.org/W1994181006","https://openalex.org/W2911102221","https://openalex.org/W2943672508","https://openalex.org/W4285602503","https://openalex.org/W4383737174","https://openalex.org/W4320918405"],"abstract_inverted_index":{"Preference-Based":[0],"reinforcement":[1],"learning":[2,112,121,157],"(PBRL)":[3],"learns":[4],"directly":[5],"from":[6,28,113,122,158,174],"the":[7,32,44,47,50,54,58,69,76,85,147,165,172],"preferences":[8,115,163],"of":[9,46,53,60,87],"human":[10],"teachers":[11,35],"regarding":[12,49],"agent":[13,48],"behaviors":[14,86],"without":[15],"needing":[16],"meticulously":[17],"designed":[18],"reward":[19,82],"functions.":[20],"However,":[21],"existing":[22,118,136],"PBRL":[23,103,166],"methods":[24,119],"often":[25],"learn":[26],"primarily":[27],"explicit":[29,123,162],"preferences,":[30],"neglecting":[31],"possibility":[33],"that":[34,155],"may":[36,42],"choose":[37],"equal":[38,93,114,160],"preferences.":[39,94,124],"This":[40],"neglect":[41],"hinder":[43],"understanding":[45],"task":[51],"perspective":[52],"teacher,":[55],"leading":[56],"to":[57,134,168],"loss":[59],"important":[61],"information.":[62],"To":[63,125],"address":[64],"this":[65,97],"issue,":[66],"we":[67,99,129],"introduce":[68],"Equal":[70],"Preference":[71,106],"Learning":[72,107],"Task,":[73],"which":[74,109],"optimizes":[75],"neural":[77],"network":[78],"by":[79],"promoting":[80],"similar":[81],"predictions":[83],"when":[84],"two":[88],"agents":[89],"are":[90],"labeled":[91],"as":[92],"Building":[95],"on":[96],"task,":[98],"propose":[100],"a":[101],"novel":[102],"method,":[104],"Multi-Type":[105],"(MTPL),":[108],"allows":[110],"simultaneous":[111,156],"while":[116],"leveraging":[117],"for":[120],"validate":[126],"our":[127],"approach,":[128],"design":[130],"experiments":[131],"applying":[132],"MTPL":[133],"four":[135],"state-of-the-art":[137],"baselines":[138],"across":[139],"ten":[140],"locomotion":[141],"and":[142,161],"robotic":[143],"manipulation":[144],"tasks":[145],"in":[146],"DeepMind":[148],"Control":[149],"Suite.":[150],"The":[151],"experimental":[152],"results":[153],"indicate":[154],"both":[159],"enables":[164],"method":[167],"more":[169],"comprehensively":[170],"understand":[171],"feedback":[173,178],"teachers,":[175],"thereby":[176],"enhancing":[177],"efficiency.":[179],"Project":[180],"page:":[181],"https://github.com/FeiCuiLengMMbb/paper_MTPL":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}