{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T13:34:34Z","timestamp":1768311274725,"version":"3.49.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"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":[[2025,12,9]]},"DOI":"10.1109\/cdc57313.2025.11312058","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"4182-4187","source":"Crossref","is-referenced-by-count":0,"title":["Plan for the Worst with Advice: Advice-augmented Robust Markov Decision Processes"],"prefix":"10.1109","author":[{"given":"Tinashe","family":"Handina","sequence":"first","affiliation":[{"name":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,CA,USA,91125"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kishan","family":"Panaganti","sequence":"additional","affiliation":[{"name":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,CA,USA,91125"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Mazumdar","sequence":"additional","affiliation":[{"name":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,CA,USA,91125"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Wierman","sequence":"additional","affiliation":[{"name":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,CA,USA,91125"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-18324-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolmodel.2008.12.023"},{"key":"ref3","author":"Shin","year":"2015","journal-title":"MDP formulation and solution algorithms for inventory management with multiple suppliers and supply"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0129"},{"key":"ref5","first-page":"3296","article-title":"Competitive caching with machine learned advice","volume-title":"Proceedings of the 35th International Conference on Machine Learning, volume 80 of Proceedings of Machine Learning Research","author":"Lykouris"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1050.0216"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0540"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2016.0786"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0566"},{"key":"ref10","first-page":"511","article-title":"Robust reinforcement learning using least squares policy iteration with provable performance guarantees","volume-title":"International Conference on Machine Learning","author":"Panaganti"},{"key":"ref11","first-page":"3331","article-title":"Finite-sample regret bound for distributionally robust offline tabular reinforcement learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Zhou"},{"key":"ref12","first-page":"9582","article-title":"Sample complexity of robust reinforcement learning with a generative model","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Panaganti"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2495174"},{"key":"ref14","article-title":"Beyond confidence regions: Tight bayesian ambiguity sets for robust mdps","author":"Russel","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2025.3567002\/mm1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1287\/ijoo.2024.0047"},{"key":"ref18","first-page":"1","article-title":"Meta-adaptive nonlinear control: Theory and algorithms","volume":"34","author":"Shi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"ref19","first-page":"1386","article-title":"Adaptive robust model predictive control via uncertainty cancellation","volume":"67","author":"Sinha","year":"2021","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref20","article-title":"A meta-mdp approach to exploration for lifelong reinforcement learning","volume":"32","author":"Garcia","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","first-page":"22591","article-title":"Distributionally adaptive meta reinforcement learning","volume":"35","author":"Ajay","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","first-page":"24414","article-title":"Robust policy learning over multiple uncertainty sets","volume-title":"International Conference on Machine Learning","author":"Xie"},{"key":"ref23","author":"Beck","year":"2023","journal-title":"A survey of meta-reinforcement learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2071379.2071381"},{"key":"ref25","article-title":"Machine learning can boost the value of wind energy","author":"Elkin","year":"2019","journal-title":"DeepMind Blog"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3508467.3508473"},{"key":"ref27","author":"Li","year":"2024","journal-title":"Safe exploitative play with untrusted type beliefs"},{"key":"ref28","first-page":"59:1","article-title":"Learnable and Instance-Robust Predictions for Online Matching, Flows and Load Balancing","volume-title":"29th Annual European Symposium on Algorithms (ESA 2021), volume 204 of Leibniz International Proceedings in Informatics (LIPIcs)","author":"Lavastida"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3579442"},{"key":"ref30","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proceedings of the Sixteenth International Conference on Machine Learning, ICML \u201999","author":"Ng"},{"key":"ref31","first-page":"792","article-title":"Principled methods for advising reinforcement learning agents","volume-title":"Proceedings of the Twentieth International Conference on International Conference on Machine Learning, ICML\u201903","author":"Wiewiora"},{"key":"ref32","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume-title":"Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research","author":"MacGlashan"},{"key":"ref34","first-page":"21885","article-title":"Widening the pipeline in human-guided reinforcement learning with explanation and context-aware data augmentation","volume":"34","author":"Guan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","article-title":"Beyond black-box advice: learning-augmented algorithms for mdps with q-value predictions","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS \u201923","author":"Li"},{"key":"ref36","first-page":"4548","article-title":"Can q-learning be improved with advice?","volume-title":"Proceedings of Thirty Fifth Conference on Learning Theory, volume 178 of Proceedings of Machine Learning Research","author":"Golowich"},{"key":"ref37","volume-title":"Plan for the worst with advice: Advice-augmented robust markov decision processes","author":"Handina"}],"event":{"name":"2025 IEEE 64th Conference on Decision and Control (CDC)","location":"Rio de Janeiro, Brazil","start":{"date-parts":[[2025,12,9]]},"end":{"date-parts":[[2025,12,12]]}},"container-title":["2025 IEEE 64th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11311984\/11311968\/11312058.pdf?arnumber=11312058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:25:25Z","timestamp":1768292725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312058","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}