{"id":"https://openalex.org/W7124178435","doi":"https://doi.org/10.1109/icpads67057.2025.11323099","title":"DRL-VLA: An Optimization Method for VLA Model Based on Deep Reinforcement Learning","display_name":"DRL-VLA: An Optimization Method for VLA Model Based on Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124178435","doi":"https://doi.org/10.1109/icpads67057.2025.11323099"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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/A5100695047","display_name":"Mu Zhang","orcid":"https://orcid.org/0000-0001-5905-9515"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengkun Zhang","raw_affiliation_strings":["China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101533004","display_name":"Pengfei Gao","orcid":"https://orcid.org/0000-0002-8093-5062"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Gao","raw_affiliation_strings":["China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037202272","display_name":"Yinuo Sheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinuo Sheng","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123007347","display_name":"Ran Li","orcid":null},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Li","raw_affiliation_strings":["China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123026096","display_name":"Qingliang An","orcid":null},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingliang An","raw_affiliation_strings":["China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443644","display_name":"Wenxin Wang","orcid":"https://orcid.org/0000-0002-8189-3124"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Wang","raw_affiliation_strings":["China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Unicom (Heilongjiang) Industrial Internet Co., Ltd.,Harbin,China","institution_ids":["https://openalex.org/I6507939"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.57252405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6093000173568726,"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":0.6093000173568726,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.18569999933242798,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.07850000262260437,"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/generalization","display_name":"Generalization","score":0.8141000270843506},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6736000180244446},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6057999730110168},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5896999835968018},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5160999894142151},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4189000129699707},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3797000050544739},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.3467000126838684}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8141000270843506},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739999890327454},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6736000180244446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6636000275611877},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6057999730110168},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5896999835968018},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5532000064849854},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4189000129699707},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3797000050544739},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2994000017642975},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5217476487159729,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2109169869","https://openalex.org/W2767263466","https://openalex.org/W2968340082","https://openalex.org/W3131140628","https://openalex.org/W3206827162","https://openalex.org/W4385430679","https://openalex.org/W4388720459","https://openalex.org/W4401416041","https://openalex.org/W4402354003","https://openalex.org/W4402727730","https://openalex.org/W4402739608","https://openalex.org/W4402753977","https://openalex.org/W4402772268","https://openalex.org/W4402776554","https://openalex.org/W4405785009","https://openalex.org/W4405785041","https://openalex.org/W4407874080","https://openalex.org/W4413147465","https://openalex.org/W4414079054","https://openalex.org/W4415798988","https://openalex.org/W4416750361"],"related_works":[],"abstract_inverted_index":{"Mobile":[0],"manipulation":[1,99],"is":[2],"a":[3,181],"crucial":[4],"stage":[5],"in":[6,16,55],"the":[7,137,163],"development":[8],"of":[9,166,184],"robotics,":[10],"enabling":[11,96],"robots":[12],"to":[13,59,71,93,125,179],"assist":[14],"humans":[15],"diverse":[17],"everyday":[18],"tasks.":[19],"However,":[20],"task":[21,141],"diversity":[22],"and":[23,105,118,122,131,142],"varying":[24],"environments":[25],"remain":[26],"major":[27],"challenges.":[28],"In":[29],"recent":[30],"years,":[31],"Vision-Language-Action":[32],"(VLA)":[33],"models":[34,58],"have":[35],"made":[36],"remarkable":[37],"progress,":[38],"demonstrating":[39],"strong":[40,164],"generalization":[41,102,165],"capabilities,":[42],"yet":[43],"they":[44],"are":[45],"primarily":[46],"developed":[47],"for":[48,115,157],"fixed-base":[49,91,158],"manipulation.":[50],"A":[51],"key":[52],"difficulty":[53],"lies":[54],"adapting":[56],"these":[57],"mobile":[60,94,98],"manipulation,":[61],"as":[62],"training":[63,124],"VLA":[64,88,159,168],"model":[65,89],"separately":[66],"from":[67,90],"navigation":[68,132],"modules":[69],"leads":[70],"error":[72],"accumulation.":[73],"To":[74],"address":[75],"this,":[76],"we":[77,108],"propose":[78],"DRL-VLA,":[79],"an":[80],"efficient":[81],"policy":[82,116],"optimization":[83,117],"framework":[84],"that":[85,146],"transfers":[86],"pre-trained":[87],"settings":[92],"bases,":[95],"coordinated":[97],"with":[100,174],"enhanced":[101],"across":[103],"tasks":[104,144],"environments.":[106],"Specifically,":[107],"design":[109],"two":[110],"Markov":[111],"Decision":[112],"Processes":[113],"(MDP)":[114],"employ":[119],"alternating":[120],"single-":[121],"dual-round":[123],"determine":[126],"both":[127],"optimal":[128],"arm":[129],"poses":[130],"positions.":[133],"Extensive":[134],"experiments":[135],"on":[136],"Open-X":[138],"dataset,":[139],"OVMM":[140],"real-world":[143,177],"demonstrate":[145],"DRL-VLA":[147],"achieves":[148],"significantly":[149],"higher":[150],"success":[151,182],"rates":[152],"than":[153],"conventional":[154],"transfer":[155],"methods":[156],"model.":[160],"Moreover,":[161],"leveraging":[162],"pretrained":[167],"model,":[169],"our":[170],"approach":[171],"requires":[172],"fine-tuning":[173],"only":[175],"100":[176],"samples":[178],"reach":[180],"rate":[183],"55":[185],"%.":[186]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-15T00:00:00"}