{"id":"https://openalex.org/W7140205806","doi":"https://doi.org/10.48550/arxiv.2603.20607","title":"Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models","display_name":"Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-03-21","ids":{"openalex":"https://openalex.org/W7140205806","doi":"https://doi.org/10.48550/arxiv.2603.20607"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.20607","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20607","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.20607","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhang, Zhilong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Zhilong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ren, Haoxiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Haoxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sun, Yihao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sheng, Yifei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng, Yifei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Haonan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haonan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lin, Haoxin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Haoxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wu, Zhichao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zhichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bacon, Pierre-Luc","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bacon, Pierre-Luc","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yu, Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5144000053405762,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5144000053405762,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.22280000150203705,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0812000036239624,"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":0.7949000000953674},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.708899974822998},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5224000215530396},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5059999823570251},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5059999823570251},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5023000240325928},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.32519999146461487}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7949000000953674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7558000087738037},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.708899974822998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6121000051498413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5619000196456909},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.32519999146461487},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.20607","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20607","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.20607","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20607","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"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":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2,30,34,61,89],"show":[3],"strong":[4],"generalization":[5],"for":[6,91,138],"robotic":[7,140],"control,":[8],"but":[9,38],"finetuning":[10],"them":[11],"with":[12],"reinforcement":[13],"learning":[14],"(RL)":[15],"is":[16],"constrained":[17],"by":[18],"the":[19],"high":[20],"cost":[21],"and":[22,48,62,105,116,120,130,136],"safety":[23],"risks":[24],"of":[25],"real-world":[26,121,139],"interaction.":[27],"Training":[28],"VLA":[29,76],"in":[31,75],"interactive":[32],"world":[33,44,93],"avoids":[35],"these":[36,73],"issues":[37],"introduces":[39],"several":[40],"challenges,":[41],"including":[42],"pixel-level":[43],"modeling,":[45],"multi-view":[46,103],"consistency,":[47],"compounding":[49],"errors":[50],"under":[51],"sparse":[52],"rewards.":[53],"Building":[54],"on":[55],"recent":[56],"advances":[57],"across":[58,118],"large":[59],"multimodal":[60,88],"model-based":[63],"RL,":[64],"we":[65],"propose":[66],"VLA-MBPO,":[67],"a":[68],"practical":[69],"framework":[70],"to":[71,101,110],"tackle":[72],"problems":[74],"finetuning.":[77],"Our":[78],"approach":[79],"has":[80],"three":[81],"key":[82],"design":[83],"choices:":[84],"(i)":[85],"adapting":[86],"unified":[87],"(UMMs)":[90],"data-efficient":[92],"modeling;":[94],"(ii)":[95],"an":[96],"interleaved":[97],"view":[98],"decoding":[99],"mechanism":[100],"enforce":[102],"consistency;":[104],"(iii)":[106],"chunk-level":[107],"branched":[108],"rollout":[109],"mitigate":[111],"error":[112],"compounding.":[113],"Theoretical":[114],"analysis":[115],"experiments":[117],"simulation":[119],"tasks":[122],"demonstrate":[123],"that":[124],"VLA-MBPO":[125],"significantly":[126],"improves":[127],"policy":[128],"performance":[129],"sample":[131],"efficiency,":[132],"underscoring":[133],"its":[134],"robustness":[135],"scalability":[137],"deployment.":[141]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-03-25T00:00:00"}