{"id":"https://openalex.org/W4416922295","doi":"https://doi.org/10.1109/tnnls.2025.3636176","title":"Model-Based Offline Reinforcement Learning With Adversarial Data Augmentation","display_name":"Model-Based Offline Reinforcement Learning With Adversarial Data Augmentation","publication_year":2025,"publication_date":"2025-12-02","ids":{"openalex":"https://openalex.org/W4416922295","doi":"https://doi.org/10.1109/tnnls.2025.3636176","pmid":"https://pubmed.ncbi.nlm.nih.gov/41329586"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3636176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3636176","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5102714720","display_name":"Hongye Cao","orcid":"https://orcid.org/0000-0002-2537-2295"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongye Cao","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2537-2295","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663869","display_name":"Fan Feng","orcid":"https://orcid.org/0000-0002-3043-2360"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fan Feng","raw_affiliation_strings":["Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3043-2360","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066091819","display_name":"Jing Huo","orcid":"https://orcid.org/0000-0002-8504-455X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Huo","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8504-455X","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764370","display_name":"Shangdong Yang","orcid":"https://orcid.org/0000-0001-5379-9539"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangdong Yang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5379-9539","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400486","display_name":"Meng Fang","orcid":"https://orcid.org/0000-0001-6745-286X"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Meng Fang","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, U.K"],"raw_orcid":"https://orcid.org/0000-0001-6745-286X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, U.K","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101619771","display_name":"Tianpei Yang","orcid":"https://orcid.org/0000-0002-5497-7146"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianpei Yang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5497-7146","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2488-1813","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":0.19104121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"6","first_page":"2592","last_page":"2606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.218299999833107,"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":0.218299999833107,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.15139999985694885,"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":0.1404999941587448,"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":0.8400999903678894},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7612000107765198},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5842000246047974},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4772000014781952},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.4088999927043915},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3912000060081482},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.38190001249313354},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.36480000615119934}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8400999903678894},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7612000107765198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282999753952026},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6341999769210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6072999835014343},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5842000246047974},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.4088999927043915},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.3614000082015991},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3636176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3636176","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:41329586","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41329586","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G164294078","display_name":null,"funder_award_id":"62506157","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2328581383","display_name":null,"funder_award_id":"62276128","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2767813700","display_name":null,"funder_award_id":"62192783","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3352541487","display_name":null,"funder_award_id":"BK20243051","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G5614591551","display_name":null,"funder_award_id":"14380128","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7334411499","display_name":null,"funder_award_id":"62206133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320317102","display_name":"National Center of Science and Technology Evaluation","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Model-based":[0,63],"offline":[1,9,47,149,170],"reinforcement":[2],"learning":[3,20,66,177],"(RL)":[4],"constructs":[5],"environment":[6,52],"models":[7,91,103],"from":[8],"datasets":[10],"to":[11,30,41,53,85,92,147],"perform":[12],"conservative":[13,28],"policy":[14,105,123,176],"optimization.":[15,124],"Existing":[16],"approaches":[17],"focus":[18],"on":[19,160],"state":[21],"transitions":[22],"through":[23],"ensemble":[24,90,102],"models,":[25,115],"rolling":[26],"out":[27],"estimation":[29,112],"mitigate":[31],"extrapolation":[32],"errors.":[33],"However,":[34],"the":[35,51,76,110,119,133,161],"static":[36],"data":[37,69,83,121],"makes":[38],"it":[39],"challenging":[40],"develop":[42],"a":[43,126],"robust":[44],"policy,":[45],"and":[46,178],"agents":[48],"cannot":[49],"access":[50],"gather":[54],"new":[55],"data.":[56,95],"To":[57],"address":[58],"these":[59],"challenges,":[60],"we":[61,74],"introduce":[62],"Offline":[64],"Reinforcement":[65],"with":[67,89],"AdversariaL":[68],"augmentation":[70,84],"(MORAL).":[71],"In":[72],"MORAL,":[73],"replace":[75],"fixed":[77,114],"horizon":[78,153],"rollout":[79,152],"by":[80],"employing":[81],"adversarial":[82,98,134],"execute":[86],"alternating":[87],"sampling":[88],"enrich":[93],"training":[94,120],"Specifically,":[96],"this":[97],"process":[99,135],"dynamically":[100],"selects":[101],"against":[104],"for":[106,122,136],"biased":[107],"sampling,":[108],"mitigating":[109],"optimistic":[111],"of":[113,175],"thus":[116],"robustly":[117],"expanding":[118],"Moreover,":[125],"differential":[127],"factor":[128],"(DF)":[129],"is":[130],"integrated":[131],"into":[132],"regularization,":[137],"ensuring":[138],"error":[139],"minimization":[140],"in":[141,173],"extrapolations.":[142],"This":[143],"data-augmented":[144],"optimization":[145],"adapts":[146],"diverse":[148],"tasks":[150],"without":[151],"tuning,":[154],"showing":[155],"remarkable":[156],"applicability.":[157],"Extensive":[158],"experiments":[159],"D4RL":[162],"benchmark":[163],"demonstrate":[164],"that":[165],"MORAL":[166],"outperforms":[167],"other":[168],"model-based":[169],"RL":[171],"methods":[172],"terms":[174],"sample":[179],"efficiency.":[180]},"counts_by_year":[],"updated_date":"2026-06-04T06:14:18.571774","created_date":"2025-12-02T00:00:00"}