{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T06:05:31Z","timestamp":1782281131989,"version":"3.54.5"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,11]]},"DOI":"10.1109\/iccps68698.2026.00018","type":"proceedings-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T19:43:46Z","timestamp":1782243826000},"page":"106-117","source":"Crossref","is-referenced-by-count":0,"title":["LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy"],"prefix":"10.1109","author":[{"given":"Hsin-Jung","family":"Yang","sequence":"first","affiliation":[{"name":"Iowa State University,Dept. of Mechanical Engineering,Ames,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanhong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Iowa State University,Translational AI Center,Ames,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prajwal","family":"Koirala","sequence":"additional","affiliation":[{"name":"Cornell University,Sibley School of Mechanical and Aerospace Engineering,Ithaca,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qisai","family":"Liu","sequence":"additional","affiliation":[{"name":"Iowa State University,Dept. of Mechanical Engineering,Ames,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cody","family":"Fleming","sequence":"additional","affiliation":[{"name":"Iowa State University,Dept. of Mechanical Engineering,Ames,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soumik","family":"Sarkar","sequence":"additional","affiliation":[{"name":"Iowa State University,Dept. of Mechanical Engineering,Ames,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124466"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.104868"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3522"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.03.072"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3078462"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/j.aiopen.2024.08.005","article-title":"A study of natural robustness of deep reinforcement learning algorithms towards adversarial perturbations","volume":"5","author":"Liu","year":"2024","journal-title":"AI Open"},{"issue":"04","key":"ref10","first-page":"4577","article-title":"Spatiotemporally constrained action space attacks on deep reinforcement learning agents","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Lee"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20855"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33726"},{"key":"ref13","article-title":"Latent safety-constrained policy approach for safe offline reinforcement learning","author":"Koirala","year":"2024","journal-title":"arXiv preprint arXiv:2412.08794"},{"key":"ref14","article-title":"Fawac: Feasibility informed advantage weighted regression for persistent safety in offline reinforcement learning","year":"2024","journal-title":"arXiv preprint arXiv:2412.08880"},{"key":"ref15","article-title":"Safe offline reinforcement learning with feasibility-guided diffusion model","author":"Zheng","year":"2024","journal-title":"arXiv preprint arXiv:2401.10700"},{"key":"ref16","article-title":"A primal-dual algorithm for offline constrained reinforcement learning with linear mdps","author":"Hong","year":"2024","journal-title":"arXiv preprint arXiv:2402.04493"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16937"},{"key":"ref18","article-title":"Offline rl with observation histories: Analyzing and improving sample complexity","author":"Hong","year":"2023","journal-title":"arXiv preprint arXiv:2310.20663"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/476"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3226579"},{"key":"ref21","article-title":"Multi-objective linear reinforcement learning with lexicographic rewards","volume-title":"Forty-second International Conference on Machine Learning","author":"Xue"},{"key":"ref22","article-title":"Prioritized soft q-decomposition for lexicographic reinforcement learning","author":"Rietz","year":"2023","journal-title":"arXiv preprint arXiv:2310.02360"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3233\/faia240841"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0625"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3457538"},{"key":"ref26","first-page":"3703","article-title":"Batch policy learning under constraints","volume-title":"International Conference on Machine Learning","author":"Le"},{"key":"ref27","first-page":"17801","article-title":"Constrained offline policy optimization","volume-title":"International Conference on Machine Learning.","author":"Polosky"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0245"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3136"},{"key":"ref30","article-title":"Safe offline reinforcement learning using trajectory-level diffusion models","volume-title":"ICRA 2024 Workshop {\\textemdash} Back to the Future: Robot Learning Going Probabilistic","author":"R\u00f6mer"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.65109\/DHBE7400"},{"key":"ref32","article-title":"Reward-safety balance in offline safe rl via diffusion regularization","author":"Guo","year":"2025","journal-title":"arXiv preprint arXiv:2502.12391"},{"key":"ref33","first-page":"63","article-title":"Revisiting multi-objective mdps with relaxed lexicographic p","volume-title":"AAAI Fall Symposia","author":"Pineda"},{"key":"ref34","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv preprint arXiv:2110.06169"},{"key":"ref35","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019","journal-title":"arXiv preprint arXiv:1910.00177"},{"key":"ref36","first-page":"11 480","article-title":"Crpo: A new approach for safe reinforcement learning with convergence guarantee","volume-title":"International Conference on Machine Learning","author":"Xu"},{"key":"ref37","first-page":"6683","article-title":"Bellman-consistent pessimism for offline reinforcement learning","volume":"34","author":"Xie","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref38","first-page":"27 395","article-title":"Policy finetuning: Bridging sample-efficient offline and online reinforcement learning","volume":"34","author":"Xie","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2022.3185139"},{"issue":"Nov","key":"ref40","first-page":"463","article-title":"Rademacher and gaussian complexities: Risk bounds and structural results","volume":"3","author":"Bartlett","year":"2002","journal-title":"Journal of machine learning research"},{"key":"ref41","first-page":"1042","article-title":"Information-theoretic considerations in batch reinforcement learning","volume-title":"International conference on machine learning","author":"Chen"},{"issue":"5","key":"ref42","article-title":"Finite-time bounds for fitted value iteration","volume":"9","author":"Munos","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref43","volume-title":"Neural network learning: Theoretical foundations","author":"Anthony","year":"2009"},{"key":"ref44","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proceedings of the nineteenth international conference on machine learning","author":"Kakade"},{"key":"ref45","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IAVVC63304.2024.10786471"},{"key":"ref47","article-title":"Datasets and benchmarks for offline safe reinforcement learning","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv:2306.09303"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref49","volume-title":"Bullet-safety-gym: A framework for constrained reinforcement learning","author":"Gronauer","year":"2022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0831"},{"key":"ref51","article-title":"Coptidice: Offline constrained reinforcement learning via stationary distribution correction estimation","author":"Lee","year":"2022","journal-title":"arXiv preprint arXiv:2204.08957"}],"event":{"name":"2026 ACM\/IEEE 17th International Conference on Cyber-Physical Systems (ICCPS)","location":"Saint Malo, France","start":{"date-parts":[[2026,5,11]]},"end":{"date-parts":[[2026,5,14]]}},"container-title":["2026 ACM\/IEEE 17th International Conference on Cyber-Physical Systems (ICCPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11570664\/11570679\/11570722.pdf?arnumber=11570722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:28:17Z","timestamp":1782278897000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11570722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,11]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccps68698.2026.00018","relation":{},"subject":[],"published":{"date-parts":[[2026,5,11]]}}}