{"id":"https://openalex.org/W4413925228","doi":"https://doi.org/10.1109/icra55743.2025.11128601","title":"MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models","display_name":"MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925228","doi":"https://doi.org/10.1109/icra55743.2025.11128601"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101575772","display_name":"Han Zhao","orcid":"https://orcid.org/0000-0003-1158-0779"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Zhao","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenxuan Song","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenxuan Song","raw_affiliation_strings":["Monash University,AIM Lab, Faculty of IT,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,AIM Lab, Faculty of IT,Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665181","display_name":"Donglin Wang","orcid":"https://orcid.org/0000-0002-8188-3735"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donglin Wang","raw_affiliation_strings":["MiLAB, Westlake University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLAB, Westlake University,China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109744862","display_name":"Xinyang Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyang Tong","raw_affiliation_strings":["MiLAB, Westlake University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLAB, Westlake University,China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060665856","display_name":"Pengxiang Ding","orcid":"https://orcid.org/0000-0002-4049-7467"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengxiang Ding","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020636384","display_name":"Xuelian Cheng","orcid":"https://orcid.org/0009-0002-7014-5304"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuelian Cheng","raw_affiliation_strings":["Monash University,AIM Lab, Faculty of IT,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,AIM Lab, Faculty of IT,Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005014252","display_name":"Zongyuan Ge","orcid":"https://orcid.org/0000-0002-5880-8673"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zongyuan Ge","raw_affiliation_strings":["Monash University,AIM Lab, Faculty of IT,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,AIM Lab, Faculty of IT,Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6545,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96570154,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11212","last_page":"11218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9853000044822693,"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":0.9853000044822693,"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":0.8510850071907043},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8165161609649658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7499798536300659},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5600893497467041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47090578079223633},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38290753960609436}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8510850071907043},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8165161609649658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7499798536300659},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5600893497467041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47090578079223633},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38290753960609436},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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":6,"referenced_works":["https://openalex.org/W4303449827","https://openalex.org/W4389666171","https://openalex.org/W4390874575","https://openalex.org/W4401415287","https://openalex.org/W4401415888","https://openalex.org/W4405787226"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2389214306","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548"],"abstract_inverted_index":{"Developing":[0],"versatile":[1],"quadruped":[2,33,174],"robots":[3,34],"that":[4,35,131],"can":[5],"smoothly":[6],"perform":[7],"various":[8],"actions":[9],"and":[10,125,140,162],"tasks":[11],"in":[12,145,153,173],"real-world":[13,154],"environments":[14],"remains":[15],"a":[16,22,48,64,72,85,94,104,164],"significant":[17],"challenge.":[18],"This":[19,76],"paper":[20],"introduces":[21],"novel":[23],"vision-language-action":[24],"(VLA)":[25],"model,":[26],"mixture":[27],"of":[28,51,88,112,159],"robotic":[29],"experts":[30,62],"(MoRE),":[31],"for":[32,42,167],"aim":[36],"to":[37,81,84,99],"introduce":[38],"reinforcement":[39,95],"learning":[40,116,172],"(RL)":[41],"fine-tuning":[43],"large-scale":[44],"VLA":[45],"models":[46],"with":[47],"large":[49,67],"amount":[50],"mixed-quality":[52,120],"data.":[53],"MoRE":[54,132],"integrates":[55],"multiple":[56],"low-rank":[57],"adaptation":[58],"modules":[59],"as":[60,103],"distinct":[61],"within":[63],"dense":[65],"multi-modal":[66],"language":[68],"model":[69,80,102,126],"(MLLM),":[70],"forming":[71],"sparse-activated":[73],"mixture-of-experts":[74],"model.":[75],"design":[77],"enables":[78],"the":[79,109,157],"effectively":[82],"adapt":[83],"wide":[86],"array":[87],"downstream":[89],"tasks.":[90,114],"Moreover,":[91],"we":[92],"employ":[93],"learning-based":[96],"training":[97],"objective":[98],"train":[100],"our":[101,113,151,160],"Q-function":[105],"after":[106],"deeply":[107],"exploring":[108],"structural":[110],"properties":[111],"Effective":[115],"from":[117],"automatically":[118],"collected":[119],"data":[121,123],"enhances":[122],"efficiency":[124],"performance.":[127],"Extensive":[128],"experiments":[129],"demonstrate":[130],"outperforms":[133],"all":[134],"baselines":[135],"across":[136],"six":[137],"different":[138],"skills":[139],"exhibits":[141],"superior":[142],"generalization":[143],"capabilities":[144],"out-of-distribution":[146],"scenarios.":[147],"We":[148],"further":[149],"validate":[150],"method":[152],"scenarios,":[155],"confirming":[156],"practicality":[158],"approach":[161],"laying":[163],"solid":[165],"foundation":[166],"future":[168],"research":[169],"on":[170],"multi-task":[171],"robots.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}