{"id":"https://openalex.org/W4414359480","doi":"https://doi.org/10.24963/ijcai.2025/664","title":"S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning","display_name":"S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359480","doi":"https://doi.org/10.24963/ijcai.2025/664"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/664","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5014299354","display_name":"Ni Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ni Mu","raw_affiliation_strings":["Beijing Key Laboratory of Embodied Intelligence Systems, Department of Automation, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Embodied Intelligence Systems, Department of Automation, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yao Luan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Luan","raw_affiliation_strings":["Beijing Key Laboratory of Embodied Intelligence Systems, Department of Automation, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Embodied Intelligence Systems, Department of Automation, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046252455","display_name":"Yiqin Yang","orcid":"https://orcid.org/0000-0002-8748-1964"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqin Yang","raw_affiliation_strings":["The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027787838","display_name":"Tielin Zhang","orcid":"https://orcid.org/0000-0002-5111-9891"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044965133","display_name":"Qing\u2010Shan Jia","orcid":"https://orcid.org/0000-0002-4683-7215"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Shan Jia","raw_affiliation_strings":["Beijing Key Laboratory of Embodied Intelligence Systems, Department of Automation, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Embodied Intelligence Systems, Department of Automation, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24183766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5967","last_page":"5975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12546","display_name":"Smart Parking Systems Research","score":0.6428999900817871,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12546","display_name":"Smart Parking Systems Research","score":0.6428999900817871,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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":0.7116000056266785},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5864999890327454},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4440000057220459},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.43849998712539673},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.42500001192092896},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.38519999384880066},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.366100013256073},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.35740000009536743}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7116000056266785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6758000254631042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6601999998092651},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5864999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.515500009059906},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.43849998712539673},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.3197999894618988},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C12298181","wikidata":"https://www.wikidata.org/wiki/Q7246814","display_name":"Proactive learning","level":5,"score":0.2775999903678894},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/664","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Preference-based":[0],"reinforcement":[1],"learning":[2,40,65,124,133],"(PbRL)":[3],"stands":[4],"out":[5],"by":[6,32,58,139],"utilizing":[7],"human":[8],"preferences":[9],"as":[10],"a":[11,81,101],"direct":[12],"reward":[13,20],"signal,":[14],"eliminating":[15],"the":[16,33,39,54,63,71,88,94,129,136],"need":[17],"for":[18],"intricate":[19],"engineering.":[21],"However,":[22],"despite":[23],"its":[24],"potential,":[25],"traditional":[26],"PbRL":[27,116],"methods":[28,117],"are":[29],"often":[30],"constrained":[31],"indistinguishability":[34,56],"of":[35,103,120,131],"segments,":[36],"which":[37,52],"impedes":[38],"process.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,68,79],"introduce":[46],"Skill-Enhanced":[47],"Preference":[48],"Optimization":[49],"Algorithm":[50],"(S-EPOA),":[51],"addresses":[53],"segment":[55,140],"issue":[57],"integrating":[59],"skill":[60,96],"mechanisms":[61],"into":[62],"preference":[64],"framework.":[66],"Specifically,":[67],"first":[69],"conduct":[70],"unsupervised":[72],"pretraining":[73],"to":[74,86],"learn":[75],"useful":[76],"skills.":[77],"Then,":[78],"propose":[80],"novel":[82],"query":[83],"selection":[84],"mechanism":[85],"balance":[87],"information":[89],"gain":[90],"and":[91,108,123],"distinguishability":[92],"over":[93],"learned":[95],"space.":[97],"Experimental":[98],"results":[99,127],"on":[100],"range":[102],"tasks,":[104],"including":[105],"robotic":[106],"manipulation":[107],"locomotion,":[109],"demonstrate":[110],"that":[111],"S-EPOA":[112],"significantly":[113],"outperforms":[114],"conventional":[115],"in":[118,134],"terms":[119],"both":[121],"robustness":[122],"efficiency.":[125],"The":[126],"highlight":[128],"effectiveness":[130],"skill-driven":[132],"overcoming":[135],"challenges":[137],"posed":[138],"indistinguishability.":[141]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}