Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization

no code implementations • 3 Sep 2023 • Uri Gadot, Esther Derman, Navdeep Kumar, Maxence Mohamed Elfatihi, Kfir Levy, Shie Mannor

In robust Markov decision processes (RMDPs), it is assumed that the reward and the transition dynamics lie in a given uncertainty set.

Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel

no code implementations • 9 Jun 2023 • Kaixin Wang, Uri Gadot, Navdeep Kumar, Kfir Levy, Shie Mannor

Robust Markov Decision Processes (RMDPs) provide a framework for sequential decision-making that is robust to perturbations on the transition kernel.

Decision Making reinforcement-learning +1