Neuromorphic architectures are brain inspired hardware that offer an energy efficient alternative to traditional von Neumann architectures. While clearly well suited to machine learning and artificial intelligence applications, the unique features of neuromorphic make it appealing for any application that can take advantage of them. In this talk I will present a spiking neural algorithm that estimates the state-value function of a Markov reward process while leveraging the parallel and event-driven nature of neuromorphic architectures. I will discuss the complexity of scaling the algorithm and implementation in CPU simulation and on the Loihi 2 neuromorphic hardware.