{"id":"https://openalex.org/W7123341327","doi":"https://doi.org/10.1109/lra.2026.3653285","title":"Transferring Policy of Offline Reinforcement Learning From Hybrid Dataset to Real World via Progressive Neural Network","display_name":"Transferring Policy of Offline Reinforcement Learning From Hybrid Dataset to Real World via Progressive Neural Network","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123341327","doi":"https://doi.org/10.1109/lra.2026.3653285"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3653285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3653285","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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":null,"display_name":"Pengyu Zhao","orcid":"https://orcid.org/0009-0005-1764-5344"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyu Zhao","raw_affiliation_strings":["College of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0009-0005-1764-5344","affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122858149","display_name":"Zheng Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Fang","raw_affiliation_strings":["College of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-9490-307X","affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094015238","display_name":"Tongxu Ai","orcid":"https://orcid.org/0009-0000-1565-9463"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongxu Ai","raw_affiliation_strings":["College of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0009-0000-1565-9463","affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056903330","display_name":"Eric Nichols","orcid":"https://orcid.org/0000-0003-0734-6621"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eric Nichols","raw_affiliation_strings":["Honda Research Institute Japan Company, Ltd., Wako, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0734-6621","affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company, Ltd., Wako, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122851551","display_name":"Randy Gomez","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Randy Gomez","raw_affiliation_strings":["Honda Research Institute Japan Company, Ltd., Wako, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3191-6818","affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company, Ltd., Wako, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bo He","orcid":"https://orcid.org/0000-0001-6826-4721"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo He","raw_affiliation_strings":["College of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-6826-4721","affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007458978","display_name":"G. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangliang Li","raw_affiliation_strings":["College of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-1728-5711","affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.7346,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95048859,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"11","issue":"3","first_page":"2642","last_page":"2649"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8418999910354614,"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":0.8418999910354614,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.029400000348687172,"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":0.012400000356137753,"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":0.833899974822998},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5558000206947327},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.5006999969482422},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.47099998593330383},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.42309999465942383},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4140999913215637},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.4088999927043915},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.40290001034736633}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.833899974822998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506999969482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.651199996471405},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5874000191688538},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.40290001034736633},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.28450000286102295},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3653285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3653285","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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":[{"id":"https://openalex.org/G5679633240","display_name":null,"funder_award_id":"23-2-1-153-zyyd-jch","funder_id":"https://openalex.org/F4320328636","funder_display_name":"Natural Science Foundation of Qingdao"}],"funders":[{"id":"https://openalex.org/F4320328636","display_name":"Natural Science Foundation of Qingdao","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2605102758","https://openalex.org/W2904338767","https://openalex.org/W2990747716","https://openalex.org/W4311486598","https://openalex.org/W4360584316","https://openalex.org/W4382202996","https://openalex.org/W4391621086","https://openalex.org/W4393160268","https://openalex.org/W4402459527","https://openalex.org/W4404314527","https://openalex.org/W4409347767","https://openalex.org/W4409348659"],"related_works":[],"abstract_inverted_index":{"Offline":[0,35],"reinforcement":[1],"learning":[2,152],"(Offline":[3],"RL)":[4],"provides":[5],"a":[6,68,139,203],"compelling":[7],"solution":[8],"for":[9],"applying":[10],"RL":[11,36],"in":[12,133,202],"high-risk":[13],"or":[14,32],"resourceconstrained":[15],"real-world":[16,54,72,157],"domains":[17],"such":[18],"as":[19],"healthcare,":[20],"autonomous":[21],"driving,":[22],"and":[23,45,53,74,78,86,106,114,153,186,192],"robotic":[24,135,142],"manipulation,":[25],"where":[26],"online":[27,160,210],"exploration":[28],"can":[29,174],"be":[30],"unsafe":[31],"impractical.":[33],"However,":[34],"faces":[37],"critical":[38],"challenges":[39],"arising":[40],"from":[41,67,182],"limited":[42],"data":[43,73],"coverage":[44],"potential":[46],"distributional":[47],"mismatch":[48],"between":[49,190],"the":[50,81,84,87,94,98,102,125,129,146,169,179,183,188,198],"pre-training":[51],"dataset":[52,148,185],"environment.":[55],"In":[56,162],"this":[57],"paper,":[58],"we":[59,117],"propose":[60],"to":[61,65,123,128,156,200],"allow":[62,197],"an":[63],"agent":[64,199],"learn":[66],"hybrid":[69,147,184],"dataset:":[70],"high-quality":[71],"high-diversity":[75],"simulation":[76,85,191],"data,":[77,194],"assume":[79],"that":[80,167],"dynamics":[82],"of":[83,111,207],"real":[88,130],"world":[89],"do":[90],"not":[91,175],"match,":[92],"but":[93,195],"state":[95],"space":[96],"is":[97],"same.":[99],"To":[100],"address":[101],"policy":[103,127,171,180],"extrapolation":[104],"error":[105],"potentially":[107],"catastrophic":[108],"failures":[109],"because":[110],"out-of-distribution":[112],"actions":[113],"sim-to-real":[115],"gap,":[116],"use":[118],"progressive":[119],"neural":[120],"networks":[121],"(PNNs)":[122],"transfer":[124],"offline":[126,151,170],"world.":[131],"Results":[132],"two":[134],"manipulation":[136],"tasks":[137,158],"with":[138],"six-degree-of-freedom":[140],"Ned":[141],"arm":[143],"show":[144],"that,":[145],"facilitates":[149],"faster":[150],"better":[154],"adaptation":[155],"during":[159,209],"learning.":[161,211],"addition,":[163],"further":[164],"analysis":[165],"shows":[166],"transferring":[168],"via":[172],"PNN":[173],"only":[176],"effectively":[177],"retain":[178],"learned":[181],"bridge":[187],"gap":[189],"reality":[193],"also":[196],"explore":[201],"more":[204],"diverse":[205],"distribution":[206],"samples":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-01-14T00:00:00"}