{"id":"https://openalex.org/W4405022959","doi":"https://doi.org/10.1109/lra.2024.3511402","title":"Boosting Efficient Reinforcement Learning for Vision-and-Language Navigation With Open-Sourced LLM","display_name":"Boosting Efficient Reinforcement Learning for Vision-and-Language Navigation With Open-Sourced LLM","publication_year":2024,"publication_date":"2024-12-04","ids":{"openalex":"https://openalex.org/W4405022959","doi":"https://doi.org/10.1109/lra.2024.3511402"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3511402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3511402","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","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/A5100388745","display_name":"Jiawei Wang","orcid":"https://orcid.org/0000-0001-5037-4658"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Wang","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5037-4658","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101506354","display_name":"Teng Wang","orcid":"https://orcid.org/0000-0002-1802-0435"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Wang","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1802-0435","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059258252","display_name":"Wenzhe Cai","orcid":"https://orcid.org/0000-0003-4610-3454"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhe Cai","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4610-3454","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103244021","display_name":"Lele Xu","orcid":"https://orcid.org/0000-0002-3225-0472"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lele Xu","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3225-0472","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019248683","display_name":"Changyin Sun","orcid":"https://orcid.org/0000-0001-9269-334X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyin Sun","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9269-334X","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4525,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90555759,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"10","issue":"1","first_page":"612","last_page":"619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9821000099182129,"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":0.9821000099182129,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9377999901771545,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9031999707221985,"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/boosting","display_name":"Boosting (machine learning)","score":0.8543229103088379},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6230411529541016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5260429382324219},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4006623327732086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3910348117351532},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3718471825122833}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8543229103088379},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6230411529541016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5260429382324219},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4006623327732086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3910348117351532},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3718471825122833}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3511402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3511402","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2926977875","https://openalex.org/W2962887844","https://openalex.org/W2963800628","https://openalex.org/W2963846044","https://openalex.org/W2964935470","https://openalex.org/W3034984114","https://openalex.org/W3107094551","https://openalex.org/W3165915253","https://openalex.org/W3172675210","https://openalex.org/W3175482402","https://openalex.org/W4226052928","https://openalex.org/W4284681025","https://openalex.org/W4285294723","https://openalex.org/W4312434279","https://openalex.org/W4387092545","https://openalex.org/W4390871884","https://openalex.org/W4392251692","https://openalex.org/W4393154152","https://openalex.org/W4394698889","https://openalex.org/W4396941373","https://openalex.org/W4401417232","https://openalex.org/W4402353981","https://openalex.org/W4402684154","https://openalex.org/W4402727020","https://openalex.org/W6620707391","https://openalex.org/W6751885507","https://openalex.org/W6757724268","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6803039797","https://openalex.org/W6810557439","https://openalex.org/W6846479934","https://openalex.org/W6849843017","https://openalex.org/W6854866820","https://openalex.org/W6854929498","https://openalex.org/W6871959147"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Vision-and-Language":[0,110],"Navigation":[1,111],"(VLN)":[2],"requires":[3],"an":[4],"agent":[5],"to":[6,21,62,73,87,132,163,175],"navigate":[7],"in":[8,41,96],"photo-realistic":[9],"environments":[10],"based":[11,26],"on":[12,27,138],"language":[13],"instructions.":[14],"Existing":[15],"methods":[16,37],"typically":[17],"employ":[18],"imitation":[19],"learning":[20,49,97],"train":[22],"agents.":[23],"However,":[24,65],"approaches":[25],"recurrent":[28],"neural":[29],"networks":[30],"suffer":[31],"from":[32,79],"poor":[33],"generalization,":[34],"while":[35],"transformer-based":[36],"are":[38],"too":[39],"large":[40],"scale":[42],"for":[43,69,109,194],"practical":[44,195],"deployment.":[45],"In":[46],"contrast,":[47],"reinforcement":[48],"(RL)":[50],"agents":[51,71,86,93,131],"can":[52],"overcome":[53],"dataset":[54],"limitations":[55],"and":[56,128,149,172],"learn":[57,74,88],"navigation":[58,77,117],"policies":[59,78],"that":[60,185],"adapt":[61],"environment":[63,81],"changes.":[64],"without":[66],"expert":[67],"trajectories":[68],"supervision,":[70],"struggle":[72],"effective":[75],"long-term":[76],"sparse":[80],"rewards.":[82],"Instruction":[83],"decomposition":[84],"enables":[85],"value":[89],"estimation":[90],"faster,":[91],"making":[92],"more":[94],"efficient":[95],"VLN":[98],"tasks.":[99],"We":[100],"propose":[101],"the":[102,144,178],"Decomposing":[103],"Instructions":[104],"with":[105],"Large":[106],"Language":[107],"Models":[108],"(DILLM-VLN)":[112],"method,":[113],"which":[114],"decomposes":[115],"complex":[116],"instructions":[118],"into":[119],"simple,":[120],"interpretable":[121,140],"sub-instructions":[122,135],"using":[123],"a":[124,150],"lightweight,":[125],"open-sourced":[126],"LLM":[127],"trains":[129],"RL":[130],"complete":[133],"these":[134,139],"sequentially.":[136],"Based":[137],"sub-instructions,":[141],"we":[142],"introduce":[143],"cascaded":[145],"multi-scale":[146],"attention":[147],"(CMA)":[148],"novel":[151],"multi-modal":[152],"fusion":[153],"discriminator":[154],"(MFD).":[155],"CMA":[156],"integrates":[157],"instruction":[158],"features":[159],"at":[160],"different":[161],"scales":[162],"provide":[164],"precise":[165],"textual":[166],"guidance.":[167],"MFD":[168],"combines":[169],"scene,":[170],"object,":[171],"action":[173],"information":[174],"comprehensively":[176],"assess":[177],"completion":[179],"of":[180],"sub-instructions.":[181],"Experiment":[182],"results":[183],"show":[184],"DILLM-VLN":[186],"significantly":[187],"improves":[188],"baseline":[189],"performance,":[190],"demonstrating":[191],"its":[192],"potential":[193],"applications.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}