Title: Fuzzy decision tree function approximation in reinforcement learning

Authors: Hitesh Shah, M. Gopal

Addresses: Control Group, Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi 110016, India. ' Control Group, Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi 110016, India

Abstract: Recent results on reinforcement learning regarding the convergence of control algorithms with function approximators, have shown that decision tree based reinforcement learning provides good learning performance and more reliable convergence than the neural network approach. It scales better to larger input spaces with lower memory requirements, and can solve problems that are infeasible using table lookup. However, decision tree based reinforcement learning can deal with only discrete actions. In realistic applications, it is imperative to deal with continuous states and actions. In this paper, we have proposed fuzzy decision tree based reinforcement learning that takes care of the limitations of decision tree based learning. We compare our approach with decision tree based function approximator on two bench mark problems: inverted pendulum stabilisation problem and two-link robot manipulator tracking problem.

Keywords: FQL; fuzzy Q-learning; function approximation; fuzzy decision trees; reinforcement learning; fuzzy logic; inverted pendulum stabilisation; two-link robot manipulators; robot tracking.

DOI: 10.1504/IJAISC.2010.032511

International Journal of Artificial Intelligence and Soft Computing, 2010 Vol.2 No.1/2, pp.26 - 45

Published online: 04 Apr 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article