Fast Bellman Updates for Wasserstein Distributionally Robust MDPs

Markov decision processes (MDPs) often suffer from the sensitivity issue under model ambiguity. In recent years, robust MDPs have emerged as an effective framework to overcome this challenge. Distributionally robust MDPs extend the robust MDP framework by incorporating distributional information of the uncertain model parameters to alleviate the conservative nature of robust MDPs. This paper proposes a computationally efficient solution framework for solving distributionally robust MDPs with Wasserstein ambiguity sets. By exploiting the specific problem structure, the proposed framework decomposes the optimization problems associated with distributionally robust Bellman updates into smaller subproblems, which can be solved efficiently. The overall complexity of the proposed algorithm is quasi-linear in both the numbers of states and actions when the distance metric of the Wasserstein distance is chosen to be L₁, L₂, or L_∞ norm, and so the computational cost of distributional robustness is substantially reduced. Our numerical experiments demonstrate that the proposed algorithms outperform other state-of-the-art solution methods. © 2023 Neural information processing systems foundation. All rights reserved.