In robust Markov decision processes (MDPs), the uncertainty in transition kernel is addressed by finding a policy that optimizes worst-case performance over an set of MDPs. While much literature has focused on discounted MDPs, average-reward MDPs remain largely unexplored. this paper, we focus where goal to find average reward set. We first take approach approximates using prove value function ...

We provide an equilibrium framework for modeling the behavior of agent who holds a simplified view dynamic optimization problem. The faces Markov decision process, where transition probability function determines evolution state variable as previous and agent's action. is uncertain about true has prior over set possible functions; this reflects (possibly simplified) her environment may not cont...

Abstract Finite state Markov processes and their aggregated have been extensively studied, especially in ion channel modeling reliability modeling. In field, the asymptotic behaviors of repairable systems modeled by both paid much attention to. For a process, it is well-known that limiting measures such as availability transition probability do not depend on initial process. However, for an dif...