Diuk, Carlos and Cohen, Andre and Littman, Michael
Rich representations in reinforcement learning have been studied for the purpose of enabling generalization and making learning feasible in large state spaces. We introduce Object-Oriented MDPs (OO-MDPs), a representation based on objects and their interactions, which is a natural way of modeling environments and offers important generalization opportunities. We introduce a learning algorithm for deterministic OO-MDPs, and prove a polynomial bound in its sample complexity. We illustrate the performance gains of our representation and algorithm in the well-known Taxi domain, plus a real-life videogame.
Discussion