{"id":"https://openalex.org/W4415063267","doi":"https://doi.org/10.1109/tnnls.2025.3615982","title":"Inhibiting Error Exacerbation in Offline Reinforcement Learning With Data Sparsity","display_name":"Inhibiting Error Exacerbation in Offline Reinforcement Learning With Data Sparsity","publication_year":2025,"publication_date":"2025-10-09","ids":{"openalex":"https://openalex.org/W4415063267","doi":"https://doi.org/10.1109/tnnls.2025.3615982","pmid":"https://pubmed.ncbi.nlm.nih.gov/41066285"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3615982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3615982","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":null,"display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0001-5894-3237"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5894-3237","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031886937","display_name":"Malu Zhang","orcid":"https://orcid.org/0000-0002-2345-0974"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Malu Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2345-0974","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687323","display_name":"Wenyu Chen","orcid":"https://orcid.org/0000-0002-9933-8014"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Chen","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-9933-8014","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002463311","display_name":"Siying Wang","orcid":"https://orcid.org/0000-0002-3180-0815"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siying Wang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-3180-0815","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Zhang","orcid":"https://orcid.org/0009-0000-5893-6563"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0000-5893-6563","affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiayin Li","orcid":"https://orcid.org/0009-0004-3741-5055"},"institutions":[{"id":"https://openalex.org/I4210134189","display_name":"Xiamen University Malaysia","ror":"https://ror.org/0331wa828","country_code":"MY","type":"education","lineage":["https://openalex.org/I191208505","https://openalex.org/I4210134189"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Jiayin Li","raw_affiliation_strings":["Xiamen University Malaysia, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0009-0004-3741-5055","affiliations":[{"raw_affiliation_string":"Xiamen University Malaysia, Selangor, Malaysia","institution_ids":["https://openalex.org/I4210134189"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5070-4511","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"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":0.13293487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"3","first_page":"1362","last_page":"1376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.920799970626831,"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":0.920799970626831,"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":0.7709000110626221},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6899999976158142},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4968999922275543},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.46050000190734863},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4603999853134155},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.45820000767707825},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4438999891281128},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.42660000920295715}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7709000110626221},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6899999976158142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777999997138977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5613999962806702},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4968999922275543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49380001425743103},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.45820000767707825},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.423799991607666},{"id":"https://openalex.org/C2777014857","wikidata":"https://www.wikidata.org/wiki/Q1383410","display_name":"Exacerbation","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4090000092983246},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3212999999523163},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.2754000127315521},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26840001344680786},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2605000138282776}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3615982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3615982","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:41066285","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41066285","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/G1294623083","display_name":null,"funder_award_id":"62220106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"aims":[4],"to":[5,41,52,74,101,116,152,162],"learn":[6],"effective":[7],"agents":[8],"from":[9],"previously":[10],"collected":[11],"datasets,":[12],"facilitating":[13],"the":[14,28,32,48,58,78,89,118,124,129,163,174,182],"safety":[15],"and":[16,85,143,157],"efficiency":[17],"of":[18,31,80,120,126,176,184],"RL":[19,99,193],"by":[20,165],"avoiding":[21],"real-time":[22],"interaction.":[23],"However,":[24],"in":[25],"practical":[26],"applications,":[27],"approximation":[29],"error":[30,42,68,90,103],"out-of-distribution":[33],"(OOD)":[34],"state-actions":[35],"can":[36],"cause":[37],"considerable":[38],"overestimation":[39],"due":[40],"exacerbation":[43,104],"during":[44],"training,":[45],"finally":[46],"degrading":[47],"performance.":[49,199],"In":[50,92],"contrast":[51],"prior":[53],"works":[54],"that":[55,63,196],"merely":[56],"addressed":[57],"OOD":[59],"state-actions,":[60],"we":[61,95],"discover":[62],"all":[64],"data":[65,75,81,106,121,148],"introduces":[66],"estimation":[67,114,131,156],"whose":[69],"magnitude":[70],"is":[71,83],"directly":[72],"related":[73],"sparsity.":[76],"Consequently,":[77],"impact":[79,119,175],"sparsity":[82,107,122,161],"inevitable":[84],"vital":[86],"when":[87],"inhibiting":[88],"exacerbation.":[91],"this":[93],"article,":[94],"propose":[96],"an":[97],"offline":[98,192],"approach":[100],"inhibit":[102],"with":[105,139],"(IEEDS),":[108],"which":[109],"includes":[110,133],"a":[111,141],"novel":[112],"value":[113,130,155],"method":[115],"consider":[117],"on":[123,191],"training":[125,164],"agents.":[127],"Specifically,":[128],"phase":[132],"two":[134],"innovations:":[135],"1)":[136],"replace":[137],"Q-net":[138],"V-net,":[140],"smaller":[142],"denser":[144],"state":[145,160],"space":[146],"makes":[147],"more":[149,153],"concentrated,":[150],"contributing":[151],"accurate":[154],"2)":[158],"introduce":[159],"design":[166],"state-aware-sparsity":[167,187],"Markov":[168],"decision":[169],"process":[170],"(MDP),":[171],"further":[172],"lessening":[173],"sparse":[177],"states.":[178],"We":[179],"theoretically":[180],"prove":[181],"convergence":[183],"IEEDS":[185],"under":[186],"MDP.":[188],"Extensive":[189],"experiments":[190],"benchmarks":[194],"reveal":[195],"IEEDS's":[197],"superior":[198]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-11T00:00:00"}