Regularized Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity

This paper focuses on reinforcement learning for the regularized robust Markov decision process (MDP) problem, an extension of the robust MDP framework. We first introduce the risk-sensitive MDP and establish the equivalence between risk-sensitive MDP and regularized robust MDP. This equivalence offers an alternative perspective for addressing the regularized RMDP and enables the design of efficient learning algorithms. Given this equivalence, we further derive the policy gradient theorem for the regularized robust MDP problem and prove the global convergence of the exact policy gradient method under the tabular setting with direct parameterization. We also propose a sample-based offline learning algorithm, namely the robust fitted-Z iteration (RFZI), for a specific regularized robust MDP problem with a KL-divergence regularization term and analyze the sample complexity of the algorithm. Our results are also supported by numerical simulations.