{"id":"https://openalex.org/W4387172173","doi":"https://doi.org/10.3233/faia230550","title":"VMBRL3: A Simple Visual Model-Based Reinforcement Learning Framework for Continuous Control","display_name":"VMBRL3: A Simple Visual Model-Based Reinforcement Learning Framework for Continuous Control","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387172173","doi":"https://doi.org/10.3233/faia230550"},"language":"en","primary_location":{"id":"doi:10.3233/faia230550","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230550","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230550","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230550","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043025179","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0003-4249-7767"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["School of Computer Sience and Engineering, Sun Yat-Sen University, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Sience and Engineering, Sun Yat-Sen University, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038214042","display_name":"Haitao Wang","orcid":"https://orcid.org/0000-0002-8394-6410"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Wang","raw_affiliation_strings":["School of Computer Sience and Engineering, Sun Yat-Sen University, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Sience and Engineering, Sun Yat-Sen University, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102755158","display_name":"Hejun Wu","orcid":"https://orcid.org/0000-0001-9758-5698"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hejun Wu","raw_affiliation_strings":["School of Computer Sience and Engineering, Sun Yat-Sen University, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Sience and Engineering, Sun Yat-Sen University, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34300672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9193999767303467,"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":0.9193999767303467,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8731781840324402},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7042149305343628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6977581977844238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6701475977897644},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6640000939369202},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6211094260215759},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6204190254211426},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5237512588500977},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5216501355171204},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4884766638278961},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.46048980951309204},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21987798810005188},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09984242916107178},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07652297616004944},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.05991619825363159}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8731781840324402},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7042149305343628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6977581977844238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6701475977897644},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6640000939369202},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6211094260215759},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6204190254211426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5237512588500977},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5216501355171204},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4884766638278961},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.46048980951309204},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21987798810005188},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09984242916107178},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07652297616004944},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.05991619825363159},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230550","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230550","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230550","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230550","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230550","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230550","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3373226507","display_name":null,"funder_award_id":"62272497","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387172173.pdf","grobid_xml":"https://content.openalex.org/works/W4387172173.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W834081922","https://openalex.org/W1906772730","https://openalex.org/W1957496711","https://openalex.org/W2028678875","https://openalex.org/W2126316555","https://openalex.org/W2140135625","https://openalex.org/W2257979135","https://openalex.org/W2396961959","https://openalex.org/W2551887912","https://openalex.org/W2556096037","https://openalex.org/W2766447205","https://openalex.org/W2781585732","https://openalex.org/W2859967432","https://openalex.org/W2877093712","https://openalex.org/W2896457183","https://openalex.org/W2900152462","https://openalex.org/W2923762280","https://openalex.org/W2950624398","https://openalex.org/W2950872548","https://openalex.org/W2953708620","https://openalex.org/W2954974210","https://openalex.org/W2964006217","https://openalex.org/W2975395092","https://openalex.org/W2977481643","https://openalex.org/W2981344907","https://openalex.org/W2982316857","https://openalex.org/W2987283559","https://openalex.org/W2990095073","https://openalex.org/W2992977009","https://openalex.org/W2995298643","https://openalex.org/W2997933098","https://openalex.org/W3015437096","https://openalex.org/W3030163527","https://openalex.org/W3035524453","https://openalex.org/W3091507139","https://openalex.org/W3094502228","https://openalex.org/W3115293622","https://openalex.org/W3122690883","https://openalex.org/W3125713282","https://openalex.org/W3145450063","https://openalex.org/W3166052165","https://openalex.org/W3175544090","https://openalex.org/W3175558129","https://openalex.org/W3183876471","https://openalex.org/W3186672455","https://openalex.org/W3207751759","https://openalex.org/W3210788351","https://openalex.org/W3211983881","https://openalex.org/W4221160484","https://openalex.org/W4226167593","https://openalex.org/W4281626944","https://openalex.org/W4283753019","https://openalex.org/W4287071981","https://openalex.org/W4288294128","https://openalex.org/W4288319859","https://openalex.org/W4289294484","https://openalex.org/W4292779060","https://openalex.org/W4313156423","https://openalex.org/W4315706776","https://openalex.org/W4321150118"],"related_works":["https://openalex.org/W4386228649","https://openalex.org/W2084164722","https://openalex.org/W3196155444","https://openalex.org/W3199810304","https://openalex.org/W3213291372","https://openalex.org/W3209574120","https://openalex.org/W3044458868","https://openalex.org/W4319083788","https://openalex.org/W4386462264","https://openalex.org/W4285260836"],"abstract_inverted_index":{"Unsupervised":[0],"pre-training":[1,62],"has":[2],"demonstrated":[3],"its":[4],"potential":[5],"for":[6,113],"accurately":[7],"constructing":[8],"world":[9,87,98],"models":[10,34],"in":[11,28,132],"visual":[12,75,152],"model-based":[13],"reinforcement":[14,63,109],"learning":[15,64,110],"(MBRL).":[16],"However,":[17],"such":[18],"MBRL":[19],"approaches":[20],"exhibit":[21],"limited":[22],"generalizability,":[23],"thereby":[24],"limiting":[25],"their":[26],"practicality":[27],"diverse":[29,117],"scenarios.":[30],"These":[31],"methods":[32,153],"produce":[33],"that":[35,125],"are":[36,47],"restricted":[37],"to":[38,51,81,91,104,116,150],"the":[39,71,84,143],"specific":[40],"task":[41],"they":[42],"were":[43],"trained":[44],"on,":[45],"and":[46,86,119,137,146],"not":[48],"easily":[49],"adaptable":[50],"other":[52],"tasks.":[53,139],"In":[54],"this":[55],"work,":[56],"we":[57],"introduce":[58],"a":[59,105,133],"powerful":[60],"unsupervised":[61],"(RL)":[65],"framework":[66,127],"called":[67],"VMBRL3,":[68],"which":[69],"improves":[70,129],"generalization":[72,130],"ability":[73,131],"of":[74,107,135,154],"MBRL.":[76,155],"VMBRL3":[77,141],"employs":[78],"task-agnostic":[79],"videos":[80],"pre-train":[82],"both":[83],"autoencoder":[85],"model":[88,99],"without":[89],"access":[90],"actions":[92],"or":[93],"rewards":[94],"information.":[95],"The":[96],"fine-tuned":[97],"can":[100],"then":[101],"be":[102],"applied":[103],"range":[106],"downstream":[108],"tasks,":[111],"allowing":[112],"rapid":[114],"adaptation":[115],"environments":[118],"facilitating":[120],"policy":[121],"learning.":[122],"We":[123],"demonstrate":[124],"our":[126],"significantly":[128],"variety":[134],"manipulation":[136],"locomotion":[138],"Furthermore,":[140],"doubles":[142],"sample":[144],"efficiency":[145],"overall":[147],"performance":[148],"compared":[149],"previous":[151]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}