MDPs: Learning in Varying Environments

In this paper ε-MDP-models are introduced and convergence theorems are proven using the generalized MDP framework of Szepesvári and Littman. Using this model family, we show that Q-learning is capable of finding near-optimal policies in varying environments. The potential of this new family of MDP models is illustrated via a reinforcement learning algorithm called event-learning which separates the optimization of decision making from the controller. We show that event-learning augmented by a particular controller, which gives rise to an ε-MDP, enables near optimal performance even if considerable and sudden changes may occur in the environment. Illustrations are provided on the two-segment pendulum problem.