Kernel-Based Reinforcement Learning
We consider the problem of approximating the cost-to-go functions in reinforcement learning. By mapping the state implicitly into a feature space, we perform a simple algorithm in the feature space, which corresponds to a complex algorithm in the original state space. Two kernel-based reinforcement learning algorithms, the ε -insensitive kernel based reinforcement learning (ε – KRL) and the least squares kernel based reinforcement learning (LS-KRL) are proposed. An example shows that the proposed methods can deal effectively with the reinforcement learning problem without having to explore many states.
KeywordsFeature Space Reinforcement Learning Reinforcement Learning Method Greedy Policy Eligibility Trace
Unable to display preview. Download preview PDF.
- 1.Sutton, R.S.: Learning to Predict by the Methods of Temporal Differences. Machine Learning 3, 9–44 (1988)Google Scholar
- 6.Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. Cambridge University Press, Camgbridge (2004)Google Scholar
- 7.Bertsekas, D.P.: Dynamic Programming: Deterministic and Stochastic Methods. Prentice-Hall, Englewood Cliffs (1987)Google Scholar
- 12.Platt, J.: Fast Training of Support Vector Machines Using Sequential Minimal Optimization. In: Scholkopf, B., Burges, C.J., Smola, A.J. (eds.) Advances in Kernel Methods –Support Vector Learning, pp. 185–208. MIT Press, Cambridge (1999)Google Scholar