A Survey of Current Techniques for Reinforcement Learning

This survey considers response generating systems that improve their behaviour using reinforcement learning. The di erence between unsupervised learning, supervised learning, and reinforcement learning is described. Two general problems concerning learning systems are presented; the credit assignment problem and the problem of perceptual aliasing. Notations and some general issues concerning reinforcement learning systems are presented. Reinforcement learning systems are further divided into two main classes; memory mapping and projective mapping systems. Each of these classes is described and some examples are presented. Some other approaches are mentioned that do not t into the two main classes. Finally some issues not covered by the surveyed articles are discussed, and some comments on the subject are made.