{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:37:03Z","timestamp":1761176223185,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>State-adversarial perturbations\u2014arising from sensor spoofing, environmental interference, or targeted attacks\u2014corrupt observations and invalidate state-wise optimality assumptions commonly made in IRL. We study inverse reinforcement learning (IRL) in state-adversarial MDPs (SA-MDPs) where only perturbed states are observable and propose SAMM-IRL, a max-margin IRL framework that operates purely in the belief (perturbed) space without access to clean states. In contrast to point-wise, state-wise optimality, we adopt a robust optimality notion based on the expected return over the initial-state distribution, which is well-posed under adversarial observation mappings. We prove (i) the existence of robust optimal policies in SA-MDPs, (ii) the contraction properties of intermediate RL operators under fixed and adaptive adversaries, and the iteration bounds for SAMM-IRL max-margin updates in belief space. Empirically, in discrete GridWorld and continuous control, SAMM-IRL achieves stronger reward recovery and imitation performance under adversarial observations than baselines, while maintaining stable policy updates. We further report perturbation parameters and ablation results in the main text to support reproducibility and practical deployment.<\/jats:p>","DOI":"10.3233\/faia251151","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:52:57Z","timestamp":1761126777000},"source":"Crossref","is-referenced-by-count":0,"title":["Robust Inverse Reinforcement Learning Under State Adversarial Perturbations"],"prefix":"10.3233","author":[{"given":"Mine Melodi","family":"Caliskan","sequence":"first","affiliation":[{"name":"Faculties of Electrical Engineering and Information Technology, and Computer Science, Ruhr University Bochum, 44801 Bochum, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saeed","family":"Ghoorchian","sequence":"additional","affiliation":[{"name":"Faculties of Electrical Engineering and Information Technology, and Computer Science, Ruhr University Bochum, 44801 Bochum, Germany"},{"name":"SAP SE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Setareh","family":"Maghsudi","sequence":"additional","affiliation":[{"name":"Faculties of Electrical Engineering and Information Technology, and Computer Science, Ruhr University Bochum, 44801 Bochum, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:52:57Z","timestamp":1761126777000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251151"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251151","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}