{"id":"https://openalex.org/W7161677270","doi":"https://doi.org/10.1109/access.2026.3694183","title":"Causality-Based Data-Augmentation for Offline Reinforcement Learning","display_name":"Causality-Based Data-Augmentation for Offline Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7161677270","doi":"https://doi.org/10.1109/access.2026.3694183"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3694183","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3694183","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3694183","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136479956","display_name":"Wei Zhang","orcid":"https://orcid.org/0009-0002-4317-1718"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["L3S Research Center, Leibniz University Hannover, Hanover, Germany"],"raw_orcid":"https://orcid.org/0009-0002-4317-1718","affiliations":[{"raw_affiliation_string":"L3S Research Center, Leibniz University Hannover, Hanover, Germany","institution_ids":["https://openalex.org/I4210136150","https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058294435","display_name":"Azlaan Mustafa Samad","orcid":"https://orcid.org/0000-0002-4722-0524"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Azlaan Mustafa SAMAD","raw_affiliation_strings":["L3S Research Center, Leibniz University Hannover, Hanover, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4722-0524","affiliations":[{"raw_affiliation_string":"L3S Research Center, Leibniz University Hannover, Hanover, Germany","institution_ids":["https://openalex.org/I4210136150","https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011726289","display_name":"Yuan Xue","orcid":"https://orcid.org/0000-0003-1773-6682"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yuan Xue","raw_affiliation_strings":["L3S Research Center, Leibniz University Hannover, Hanover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Leibniz University Hannover, Hanover, Germany","institution_ids":["https://openalex.org/I4210136150","https://openalex.org/I114112103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009587907","display_name":"Daniel Kudenko\u22c6","orcid":"https://orcid.org/0000-0003-3359-3255"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Kudenko","raw_affiliation_strings":["L3S Research Center, Leibniz University Hannover, Hanover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Leibniz University Hannover, Hanover, Germany","institution_ids":["https://openalex.org/I4210136150","https://openalex.org/I114112103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79385386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"76639","last_page":"76648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6651999950408936,"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":0.6651999950408936,"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":0.0272000003606081,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.021400000900030136,"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":0.6427000164985657},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.5741999745368958},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.31200000643730164},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.258899986743927},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.25220000743865967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7145000100135803},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6427000164985657},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.5741999745368958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5649999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4262000024318695},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.24709999561309814},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24410000443458557}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3694183","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3694183","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bbdfcb6b472e49b8a5e99b25c9e73d21","is_oa":true,"landing_page_url":"https://doaj.org/article/bbdfcb6b472e49b8a5e99b25c9e73d21","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 76639-76648 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3694183","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3694183","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"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],"seeks":[4],"to":[5,44,58,63],"derive":[6],"an":[7],"optimal":[8],"decision-making":[9,106,149],"policy":[10,54,80,104,161],"from":[11],"a":[12,102,120,134],"static":[13,37,66,94,97,142,165],"dataset,":[14,38],"addressing":[15],"scenarios":[16],"in":[17,130,177],"which":[18],"interaction":[19],"with":[20,167],"the":[21,36,65,75,88,92,109,125,131,141,148,152],"environment":[22],"is":[23,28,62,99],"impossible":[24],"or":[25,30],"data":[26,49,71,84],"collection":[27],"costly":[29],"risky.":[31],"The":[32,96],"inherent":[33],"limitation":[34],"of":[35,133,151],"incomplete":[39],"state-action":[40,76],"space":[41,77],"coverage,":[42],"leads":[43],"extrapolation":[45],"errors":[46],"when":[47],"out-of-distribution":[48],"points":[50,85],"are":[51],"encountered":[52],"during":[53],"training.":[55,81],"One":[56],"way":[57],"mitigate":[59],"this":[60,112],"problem":[61],"augment":[64],"dataset":[67,98,143],"by":[68,101,163],"generating":[69],"new":[70,83],"points,":[72],"thereby":[73],"broadening":[74],"available":[78],"for":[79,147,174],"These":[82],"should":[86],"follow":[87],"same":[89],"distribution":[90],"as":[91],"original":[93],"dataset.":[95],"collected":[100],"behavioral":[103],"whose":[105],"logic":[107,150],"determines":[108],"distribution.":[110],"In":[111],"work,":[113],"we":[114],"propose":[115],"Causality":[116],"Based":[117],"data-Augmentation":[118],"(CBA),":[119],"novel":[121],"framework":[122],"that":[123,158],"models":[124],"Markov":[126],"Decision":[127],"Process":[128],"(MDP)":[129],"form":[132],"Structural":[135],"Causal":[136],"Model":[137],"(SCM)":[138],"and":[139],"augments":[140],"while":[144],"explicitly":[145],"accounting":[146],"behavior":[153],"policy.":[154],"Experimental":[155],"results":[156],"demonstrate":[157],"CBA":[159],"enhances":[160],"performance":[162],"augmenting":[164],"datasets":[166],"higher":[168],"reward":[169],"transitions,":[170],"highlighting":[171],"its":[172],"potential":[173],"advancing":[175],"research":[176],"offline":[178],"RL.":[179]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-20T00:00:00"}