Skip to Main Content
In this paper, adaptive controller architecture based on a combination of temporal-difference (TD) learning and on-line variant of Random Forest (RF) is proposed. We call this implementation Random-TD. The approach iteratively improves its control strategies by exploiting only relevant parts of action and is able to learn completely in on-line mode. Such capability of on-line adaptation would take us closer to the goal of more versatile, robust and adaptable control. To illustrate this and to demonstrate the applicability of the approach, it has been applied on high-dimensional control problems (Ailerons, Elevator, Kinematics, and Friedman). The results demonstrate that our hybrid approach is perfectly adaptable and can significantly improve the performance of TD methods while speed up learning process.
Date of Conference: 4-4 Dec. 2008