Graph kernels and Gaussian processes for relational reinforcement learning

Thomas Gartner     Kurt Driessens     Jan Ramon

Abstract:
Relational reinforcement learning is a Q-learning technique for relational state-action spaces. It aims to enable agents to learn how to act in an environment that has no natural representation as a tuple of constants. In this case, the learning algorithm used to approximate the mapping between state-action pairs and their so called Q(uality)-value has to be not only very reliable, but it also has to be able to handle the relational representation of state-action pairs.

In this paper we investigate the use of Gaussian processes to approximate the quality of state-action pairs. In order to employ Gaussian processes in a relational setting we use graph kernels as the covariance function between state-action pairs. Experiments conducted in the blocks world show that Gaussian processes with graph kernels can compete with, and often improve on, regression trees and instance based regression as a generalization algorithm for relational reinforcement learning.

Published: T. Gartner, K. Driessens, en J. Ramon, Graph kernels and Gaussian processes for relational reinforcement learning, Inductive Logic Programming, 13th International Conference, ILP 2003, Proceedings (Horvath, T. and Yamamoto, A., eds.), vol 2835, Lecture Notes in Computer Science, pp. 146-163, 2003

Source: PS, Gzipped, 196248 bytes

BibTeX