{"id":"https://openalex.org/W4414360239","doi":"https://doi.org/10.24963/ijcai.2025/800","title":"Self-Consistent Model-based Adaptation for Visual Reinforcement Learning","display_name":"Self-Consistent Model-based Adaptation for Visual Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360239","doi":"https://doi.org/10.24963/ijcai.2025/800"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/800","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/800","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/A5060724443","display_name":"Xinning Zhou","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":"Xinning Zhou","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054592102","display_name":"Chengyang Ying","orcid":"https://orcid.org/0000-0003-3334-2915"},"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":"Chengyang Ying","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102394779","display_name":"Yao Feng","orcid":"https://orcid.org/0000-0002-8213-5181"},"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 Feng","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341893","display_name":"Hang Su","orcid":"https://orcid.org/0000-0003-3365-4361"},"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":"Hang Su","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100686240","display_name":"Jun Zhu","orcid":"https://orcid.org/0000-0002-1773-548X"},"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":"Jun Zhu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23632417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7191","last_page":"7199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.7817999720573425,"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/T10121","display_name":"Building Energy and Comfort Optimization","score":0.7817999720573425,"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"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.775600016117096,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6858999729156494},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6360999941825867},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6036999821662903},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5494999885559082},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5424000024795532},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.46239998936653137},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4487000107765198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228000164031982},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6858999729156494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6699000000953674},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6360999941825867},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5302000045776367},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4487000107765198},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3734999895095825},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/800","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/800","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":{"Visual":[0],"reinforcement":[1],"learning":[2],"agents":[3],"typically":[4],"face":[5],"serious":[6],"performance":[7,130],"declines":[8],"in":[9,74],"real-world":[10],"applications":[11],"caused":[12],"by":[13,102],"visual":[14,118],"distractions.":[15],"Existing":[16],"methods":[17],"rely":[18],"on":[19,116],"fine-tuning":[20],"the":[21,45,71,100,104],"policy's":[22],"representations":[23],"with":[24,54,85,109],"hand-crafted":[25],"augmentations.":[26],"In":[27],"this":[28],"work,":[29],"we":[30,78],"propose":[31],"Self-Consistent":[32],"Model-based":[33],"Adaptation":[34],"(SCMA),":[35],"a":[36,55,66,86,95,110],"novel":[37],"method":[38],"that":[39,126],"fosters":[40],"robust":[41],"adaptation":[42],"without":[43],"modifying":[44],"policy.":[46],"By":[47],"transferring":[48],"cluttered":[49],"observations":[50,108],"to":[51,98],"clean":[52,107],"ones":[53],"denoising":[56,72],"model,":[57],"SCMA":[58,127],"can":[59],"mitigate":[60],"distractions":[61,133],"for":[62],"various":[63,132],"policies":[64],"as":[65],"plug-and-play":[67],"enhancement.":[68],"To":[69],"optimize":[70,99],"model":[73],"an":[75,80],"unsupervised":[76,81],"manner,":[77],"derive":[79],"distribution":[82,105],"matching":[83],"objective":[84,101],"theoretical":[87],"analysis":[88],"of":[89,106],"its":[90],"optimality.":[91],"We":[92],"further":[93],"present":[94],"practical":[96],"algorithm":[97],"estimating":[103],"pre-trained":[111],"world":[112],"model.":[113],"Extensive":[114],"experiments":[115],"multiple":[117],"generalization":[119],"benchmarks":[120],"and":[121,134],"real":[122],"robot":[123],"data":[124],"demonstrate":[125],"effectively":[128],"boosts":[129],"across":[131],"exhibits":[135],"better":[136],"sample":[137],"efficiency.":[138]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}