← Search

Maxence Mohamed ELFATIHI

2 accepted papers

2025

Non-rectangular Robust MDPs with Normed Uncertainty Sets

NeurIPS 2025poster

Robust policy evaluation for non-rectangular uncertainty set is generally NP-hard, even in approximation. Consequently, existing approaches suffer from either exponential iteration complexity or significant accuracy gaps. Interestingly, we identify a powerful class of $L_p$-bounded uncertainty sets…

Cited by 0SourceScholar
2024

Solving Non-rectangular Reward-Robust MDPs via Frequency Regularization

AAAI 2024technical

In robust Markov decision processes (RMDPs), it is assumed that the reward and the transition dynamics lie in a given uncertainty set. By targeting maximal return under the most adversarial model from that set, RMDPs address performance sensitivity to misspecified environments. Yet, to preserve comp…

Cited by 2SourcePDFScholar