Classical AI planning considers how to change the state of the world from an initial state to a goal state given a set of possible operators. Relatively recently, the area has grown to include probabilistic domains and operators, bridging towards studies of Markov Decision Processes and learning.
Online Kernel Selection for Bayesian Reinforcement Learning Joseph Reisinger and Peter Stone and Risto Miikkulainen In Proceedings of the Twenty-Fifth International Conference on Machine Learning, July 2008. 2008