Abstraction and Generalization in Reinforcement Learning: A Summary and Framework

ion and Generalization in Reinforcement Learning: A Summary and Framework Marc Ponsen, Matthew E. Taylor, and Karl Tuyls 1 Universiteit Maastricht, Maastricht, The Netherlands {m.ponsen,k.tuyls}@maastrichtuniversity.nl 2 The University of Southern California, Los Angeles, CA [email protected] Abstract. In this paper we survey the basics of reinforcement learning, generalization and abstraction. We start with an introduction to the fundamentals of reinforcement learning and motivate the necessity for generalization and abstraction. Next we summarize the most important techniques available to achieve both generalization and abstraction in reinforcement learning. We discuss basic function approximation techniques and delve into hierarchical, relational and transfer learning. All concepts and techniques are illustrated with examples. In this paper we survey the basics of reinforcement learning, generalization and abstraction. We start with an introduction to the fundamentals of reinforcement learning and motivate the necessity for generalization and abstraction. Next we summarize the most important techniques available to achieve both generalization and abstraction in reinforcement learning. We discuss basic function approximation techniques and delve into hierarchical, relational and transfer learning. All concepts and techniques are illustrated with examples.