{"id":"https://openalex.org/W4416294393","doi":"https://doi.org/10.1109/tits.2025.3612273","title":"Self-Expert Imitation With Purifying Latent Feature for Generalization in Visual Reinforcement Learning","display_name":"Self-Expert Imitation With Purifying Latent Feature for Generalization in Visual Reinforcement Learning","publication_year":2025,"publication_date":"2025-11-13","ids":{"openalex":"https://openalex.org/W4416294393","doi":"https://doi.org/10.1109/tits.2025.3612273"},"language":null,"primary_location":{"id":"doi:10.1109/tits.2025.3612273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3612273","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Transactions on Intelligent Transportation Systems","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/A5021174592","display_name":"Lin Chen","orcid":"https://orcid.org/0000-0001-5363-7441"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Chen","raw_affiliation_strings":["School of Software Engineering, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0001-5363-7441","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418300","display_name":"Yang Mo","orcid":"https://orcid.org/0000-0001-6734-8691"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yang Mo","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-6734-8691","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025640070","display_name":"Yaonan Wang","orcid":"https://orcid.org/0000-0002-0519-6458"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yaonan Wang","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-0519-6458","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013336609","display_name":"Zhiqiang Miao","orcid":"https://orcid.org/0000-0002-0899-1537"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Miao","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-0899-1537","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021425216","display_name":"Kai Zeng","orcid":"https://orcid.org/0000-0002-2745-1253"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kai Zeng","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-2745-1253","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022848316","display_name":"Mingtao Feng","orcid":"https://orcid.org/0000-0003-0384-3743"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingtao Feng","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-0384-3743","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003351770","display_name":"Zhen Zhou","orcid":"https://orcid.org/0009-0001-2112-3742"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Zhen Zhou","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0001-2112-3742","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051208870","display_name":"Sifei Wang","orcid":"https://orcid.org/0000-0003-0997-340X"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sifei Wang","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-0997-340X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103232173","display_name":"Danwei Wang","orcid":"https://orcid.org/0000-0003-3400-0079"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Danwei Wang","raw_affiliation_strings":["School of Electrical and Electrical Engineering, Nanyang Technological University, Jurong West, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3400-0079","affiliations":[{"raw_affiliation_string":"School of Electrical and Electrical Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"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":0.16693681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","first_page":"960","last_page":"971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.34299999475479126,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.34299999475479126,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.32679998874664307,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09459999948740005,"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/generalization","display_name":"Generalization","score":0.8765000104904175},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7425000071525574},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5823000073432922},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5109999775886536},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4657999873161316},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43529999256134033},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.40529999136924744},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.39910000562667847},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.3864000141620636}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8765000104904175},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7425000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7318000197410583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7203999757766724},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5270000100135803},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5109999775886536},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31540000438690186},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.2994000017642975},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2025.3612273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3612273","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Transactions on Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1875860264","display_name":null,"funder_award_id":"2025RC3088","funder_id":"https://openalex.org/F4320330206","funder_display_name":"Science and Technology Program of Hunan Province"},{"id":"https://openalex.org/G3322184467","display_name":null,"funder_award_id":"62103141","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G649714012","display_name":null,"funder_award_id":"2025JJ50336","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G7185484708","display_name":null,"funder_award_id":"62027810","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8190209641","display_name":null,"funder_award_id":"62133005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null},{"id":"https://openalex.org/F4320330206","display_name":"Science and Technology Program of Hunan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W297279189","https://openalex.org/W2604262106","https://openalex.org/W2605102758","https://openalex.org/W2765407302","https://openalex.org/W2798434327","https://openalex.org/W2962793481","https://openalex.org/W2962977206","https://openalex.org/W2990747716","https://openalex.org/W2998508940","https://openalex.org/W3010293082","https://openalex.org/W3030981716","https://openalex.org/W3034302825","https://openalex.org/W3034781633","https://openalex.org/W3035682985","https://openalex.org/W3108145393","https://openalex.org/W3135203571","https://openalex.org/W3135642434","https://openalex.org/W3135939397","https://openalex.org/W3162767959","https://openalex.org/W3175558129","https://openalex.org/W3176485999","https://openalex.org/W3205321526","https://openalex.org/W3213722353","https://openalex.org/W4200091066","https://openalex.org/W4225108568","https://openalex.org/W4252279978","https://openalex.org/W4253802431","https://openalex.org/W4288735300","https://openalex.org/W4289639938","https://openalex.org/W4290996343","https://openalex.org/W4311415873","https://openalex.org/W4386159011","https://openalex.org/W4386736782","https://openalex.org/W4391855168","https://openalex.org/W4405785416","https://openalex.org/W4408564950","https://openalex.org/W4408609185"],"related_works":[],"abstract_inverted_index":{"The":[0],"generalization":[1,56,166,187],"ability":[2],"of":[3,26,58,84,131,196],"visual":[4,31,63],"reinforcement":[5,64],"learning,":[6],"which":[7,111],"allows":[8],"the":[9,13,27,47,55,77,82,113,124,129,132,157,176,194,197],"policy":[10,59,91,115,198],"trained":[11,114],"in":[12,19,62,81,120,135,168,189,199],"source":[14],"domain":[15],"to":[16,30,53,75,89,116,123,160,202],"guide":[17,118],"agents":[18,119,201],"similar":[20,122,171],"unknown":[21],"target":[22],"environments,":[23,191],"is":[24],"one":[25],"cores":[28],"applied":[29],"navigation":[32],"and":[33,46,147,163,185],"autonomous":[34],"driving.":[35],"Recently,":[36],"methods":[37],"such":[38],"as":[39],"data":[40],"augmentation":[41],"techniques,":[42],"self-supervised":[43],"learning":[44],"methods,":[45,69],"generative":[48],"adversarial":[49],"network":[50],"were":[51],"employed":[52],"enhance":[54],"capability":[57],"neural":[60],"networks":[61],"learning.":[65],"However,":[66],"current":[67],"state-of-the-art":[68],"after":[70],"utilizing":[71],"domain-general":[72,146,158],"latent":[73,109,149],"features":[74],"train":[76],"RL":[78],"policy,":[79],"result":[80],"loss":[83],"certain":[85],"state-specific":[86],"features,":[87,110],"leading":[88],"diminished":[90],"performance":[92,130,167,188,195],"following":[93],"generalization.":[94],"To":[95],"tackle":[96],"these":[97],"challenges,":[98],"we":[99],"designed":[100],"a":[101,139,153],"technical":[102],"framework":[103],"called":[104],"self-expert":[105],"imitation":[106],"with":[107],"purifying":[108],"enables":[112],"effectively":[117],"scenarios":[121],"training":[125],"environment,":[126],"without":[127,192],"compromising":[128,193],"policy-guided":[133],"agent":[134],"task":[136],"completion.":[137],"Additionally,":[138],"novel":[140],"method":[141],"was":[142],"developed":[143],"for":[144],"separating":[145],"domain-specific":[148],"vectors":[150],"based":[151],"on":[152,175],"variational":[154],"autoencoder,":[155],"enabling":[156],"component":[159],"exhibit":[161],"strong":[162,184],"stable":[164,186],"zero-shot":[165],"unseen":[169,190],"visually":[170],"domains.":[172],"Extensive":[173],"experiments":[174],"CarRacing":[177],"game":[178],"demonstrated":[179],"that":[180],"our":[181],"approach":[182],"achieves":[183],"guiding":[200],"complete":[203],"tasks.":[204]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-13T00:00:00"}