{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T05:06:14Z","timestamp":1779771974132,"version":"3.53.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3694183","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T19:50:38Z","timestamp":1779220238000},"page":"76639-76648","source":"Crossref","is-referenced-by-count":0,"title":["Causality-Based Data-Augmentation for Offline Reinforcement Learning"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4317-1718","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"first","affiliation":[{"name":"L3S Research Center, Leibniz University Hannover, Hanover, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4722-0524","authenticated-orcid":false,"given":"Azlaan Mustafa","family":"SAMAD","sequence":"additional","affiliation":[{"name":"L3S Research Center, Leibniz University Hannover, Hanover, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Xue","sequence":"additional","affiliation":[{"name":"L3S Research Center, Leibniz University Hannover, Hanover, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Kudenko","sequence":"additional","affiliation":[{"name":"L3S Research Center, Leibniz University Hannover, Hanover, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref3","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fujimoto"},{"key":"ref4","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref5","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv:2110.06169"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0125"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1808"},{"key":"ref8","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"ref9","first-page":"288","volume-title":"Elements of Causal Inference: Foundations and Learning Algorithms","author":"Peters","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref11","volume-title":"Counterfactuals","author":"Lewis","year":"2013"},{"key":"ref12","article-title":"Deep backtracking counterfactuals for causally compliant explanations","author":"Kladny","year":"2023","journal-title":"arXiv:2310.07665"},{"issue":"35","key":"ref13","article-title":"Back on track: Backtracking in counterfactual reasoning","volume-title":"Proc. Annu. Meeting Cogn. Sci. Soc.","volume":"35","author":"Gerstenberg"},{"key":"ref14","first-page":"177","article-title":"Backtracking counterfactuals","volume-title":"Proc. Conf. Causal Learn. Reasoning","author":"Von K\u00fcgelgen"},{"key":"ref15","article-title":"Causal reinforcement learning: A surveym","author":"Deng","year":"2023","journal-title":"arXiv:2307.01452"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3403001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1459"},{"key":"ref18","article-title":"Sample-efficient reinforcement learning via counterfactual-based data augmentation","author":"Lu","year":"2020","journal-title":"arXiv:2012.09092"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1924"},{"key":"ref20","article-title":"Model-invariant state abstractions for model-based reinforcement learning","author":"Tomar","year":"2021","journal-title":"arXiv:2102.09850"},{"key":"ref21","first-page":"3952","article-title":"Invariant causal imitation learning for generalizable policies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bica"},{"key":"ref22","first-page":"11214","article-title":"Invariant causal prediction for block mdps","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref23","first-page":"764","article-title":"Learning domain invariant representations in goal-conditioned block MDPs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref24","first-page":"22905","article-title":"Causal influence detection for improving efficiency in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Seitzer"},{"key":"ref25","first-page":"9848","article-title":"Causal curiosity: Rl agents discovering self-supervised experiments for causal representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sontakke"},{"key":"ref26","article-title":"Causal dynamics learning for task-independent state abstraction","author":"Wang","year":"2022","journal-title":"arXiv:2206.13452"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0679"},{"key":"ref28","article-title":"Hierarchical reinforcement learning for zero-shot generalization with subtask dependencies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref29","article-title":"Eden: A unified environment framework for booming reinforcement learning algorithms","author":"Chen","year":"2021","journal-title":"arXiv:2109.01768"},{"key":"ref30","first-page":"907","article-title":"S4RL: Surprisingly simple self-supervision for offline reinforcement learning in robotics","volume-title":"Proc. Conf. Robot Learn.","author":"Sinha"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2009"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0335"},{"key":"ref33","first-page":"3976","article-title":"Counterfactual data augmentation using locally factored dynamics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pitis"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1319"},{"key":"ref35","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref36","article-title":"RvS: What is essential for offline RL via supervised learning","author":"Emmons","year":"2021","journal-title":"arXiv:2112.10751"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992934"},{"key":"ref39","article-title":"Neural spline flows","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Durkan"},{"key":"ref40","article-title":"Masked autoregressive flow for density estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Papamakarios"},{"key":"ref41","article-title":"Density estimation using real NVP","author":"Dinh","year":"2016","journal-title":"arXiv:1605.08803"},{"issue":"57","key":"ref42","first-page":"1","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11522987.pdf?arnumber=11522987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T04:51:25Z","timestamp":1779771085000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11522987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3694183","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}