Author:

Abstract:

In reinforcement learning, we use probabilistic/stochastic MDP when a state value is unknown. Lots of work has been done regarding this problem. However, if the probability is not unique and changing, i.e., the uncertainty is epistemic, or the agent still needs to meet the state, we have less information. In this case, a novel idea is to use an epistemic uncertainty model and solve the MDP via an approach by generalising the Bellman equation. This poster will present this idea and show numerical results on a simple toy example.