First-order Policy Optimization for Robust Markov Decision Process

We consider the problem of solving robust Markov decision process (MDP), which involves a set of discounted, finite state, finite action space MDPs with uncertain transition kernels. The goal of planning is to find a robust policy that optimizes the worst-case values against the transition uncertainties, and thus encompasses the standard MDP planning as a special case. For $(\mathbf{s},\mathbf{a})$-rectangular uncertainty sets, we develop a policy-based first-order method, namely the robust policy mirror descent (RPMD), and establish an $\mathcal{O}(\log(1/\epsilon))$ and $\mathcal{O}(1/\epsilon)$ iteration complexity for finding an $\epsilon$-optimal policy, with two increasing-stepsize schemes. The prior convergence of RPMD is applicable to any Bregman divergence, provided the policy space has bounded radius measured by the divergence when centering at the initial policy. Moreover, when the Bregman divergence corresponds to the squared euclidean distance, we establish an $\mathcal{O}(\max \{1/\epsilon, 1/(\eta \epsilon^2)\})$ complexity of RPMD with any constant stepsize $\eta$. For a general class of Bregman divergences, a similar complexity is also established for RPMD with constant stepsizes, provided the uncertainty set satisfies the relative strong convexity. We further develop a stochastic variant, named SRPMD, when the first-order information is only available through online interactions with the nominal environment. For general Bregman divergences, we establish an $\mathcal{O}(1/\epsilon^2)$ and $\mathcal{O}(1/\epsilon^3)$ sample complexity with two increasing-stepsize schemes. For the euclidean Bregman divergence, we establish an $\mathcal{O}(1/\epsilon^3)$ sample complexity with constant stepsizes. To the best of our knowledge, all the aforementioned results appear to be new for policy-based first-order methods applied to the robust MDP problem.