Abstraction and Generalization in Reinforcement Learning: A Summary and Framework [chapter]

Marc Ponsen, Matthew E. Taylor, Karl Tuyls
2010 Lecture Notes in Computer Science  
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
more » ... niques are illustrated with examples. Description 3 vs. 2 and 4 vs. 3 State Variables 3 vs. 2 state variable 4 vs. 3 state variable dist(K1, C) dist(K1, C) dist(K1, K2) dist(K1, K2) dist(K1, K3) dist(K1, K3) dist(K1, K4) dist(K1, T1) dist(K1, T1) dist(K1, T2) dist(K1, T2) dist(K1, T3) dist(K2, C) dist(K2, C) dist(K3, C) dist(K3, C) dist(K4, C)
doi:10.1007/978-3-642-11814-2_1 fatcat:vovcchfhfrcpfat6evfefc54em