{"id":"https://openalex.org/W7131091372","doi":"https://doi.org/10.1109/robio66223.2025.11378100","title":"Reinforcement Learning with Stage-Wise Model Fusion for Sequential Object Manipulation Tasks","display_name":"Reinforcement Learning with Stage-Wise Model Fusion for Sequential Object Manipulation Tasks","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7131091372","doi":"https://doi.org/10.1109/robio66223.2025.11378100"},"language":null,"primary_location":{"id":"doi:10.1109/robio66223.2025.11378100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11378100","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 Biomimetics (ROBIO)","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/A5126584150","display_name":"Yuhan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Huang","raw_affiliation_strings":["School of Electrical, Information and Communication Engineering, Huazhong University of Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Information and Communication Engineering, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072609579","display_name":"Zijian Ning","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Ning","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775049","display_name":"Zhongyu Wang","orcid":"https://orcid.org/0000-0001-9314-4799"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyuan Wang","raw_affiliation_strings":["School of Electrical, Information and Communication Engineering, Huazhong University of Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Information and Communication Engineering, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621288","display_name":"Jiaxuan Wang","orcid":"https://orcid.org/0009-0008-0450-6857"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxuan Wang","raw_affiliation_strings":["School of Electrical, Information and Communication Engineering, Huazhong University of Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Information and Communication Engineering, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126655433","display_name":"Xiaojun Hei","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Hei","raw_affiliation_strings":["School of Electrical, Information and Communication Engineering, Huazhong University of Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Information and Communication Engineering, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47720641"],"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":"2268","last_page":"2273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8618000149726868,"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":0.8618000149726868,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.06750000268220901,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.01759999990463257,"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":0.644599974155426},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5655999779701233},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5418000221252441},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5286999940872192},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5228000283241272},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4903999865055084},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.41100001335144043},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.36899998784065247}],"concepts":[{"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/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.644599974155426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6290000081062317},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5655999779701233},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5418000221252441},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5228000283241272},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4903999865055084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4287000000476837},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.41100001335144043},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.3003000020980835},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio66223.2025.11378100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11378100","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 Biomimetics (ROBIO)","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":7,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2964227312","https://openalex.org/W3199096322","https://openalex.org/W3206737393","https://openalex.org/W4385462854","https://openalex.org/W4402583750","https://openalex.org/W4408235556"],"related_works":[],"abstract_inverted_index":{"Sequential":[0],"robotic":[1,120,142],"manipulation":[2,42],"tasks":[3,135],"present":[4],"significant":[5],"challenges,":[6],"including":[7,136],"sparse":[8],"rewards":[9],"and":[10,104,116,128,138,151],"the":[11,33,79],"tendency":[12],"for":[13,35,39,55,140,154],"compact":[14],"models":[15,54,63],"to":[16,31,82],"lose":[17],"previously":[18],"learned":[19],"skills.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"propose":[25],"a":[26,68,118,149],"multistage":[27,134],"model":[28,81,102],"fusion":[29,77],"framework":[30,153],"eliminate":[32],"need":[34],"human":[36],"expert":[37,108],"demonstrations":[38],"sequential":[40,86,141,156],"object":[41],"tasks.":[43,87],"First,":[44],"simple":[45],"reinforcement":[46],"learning":[47],"independently":[48],"trains":[49],"specialized":[50],"meta-policies":[51],"as":[52,98],"teacher":[53,62],"each":[56],"sub-task.":[57],"The":[58,159],"knowledge":[59],"from":[60],"these":[61],"is":[64],"then":[65],"aggregated":[66],"into":[67],"lightweight":[69],"Long":[70],"Short-Term":[71],"Memory":[72],"(LSTM)":[73],"student":[74,80],"model.":[75],"This":[76,88],"enables":[78],"autonomously":[83],"execute":[84],"complex":[85,155],"integrated":[89],"method":[90,146],"overcomes":[91],"key":[92],"limitations":[93],"of":[94],"traditional":[95],"approaches,":[96],"such":[97],"low":[99],"training":[100],"efficiency,":[101],"overfitting,":[103],"excessive":[105],"reliance":[106],"on":[107,117],"data.":[109],"We":[110],"conduct":[111],"evaluation":[112],"experiments":[113],"in":[114,131],"simulation":[115],"physical":[119],"arm":[121],"platform.":[122],"Our":[123,144],"results":[124],"demonstrate":[125],"superior":[126],"performance":[127],"robust":[129],"generalization":[130],"two":[132],"challenging":[133],"\u201cdrawer-opening\u201d":[137],"\u201ccoffee-making\u201d":[139],"manipulation.":[143],"proposed":[145],"may":[147],"offer":[148],"scalable":[150],"efficient":[152],"robot":[157],"operations.":[158],"source":[160],"codes":[161],"are":[162],"available":[163],"at":[164],"https://github.com/Dian-robot/FRS-Long-Sequence-Reinforcement-Learning.git.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-24T00:00:00"}