Adaptive Agent Design Based on Reinforcement Learning and Tracking

AI seems to be developing toward a theory of intelligent agents (IA), however, the theoretical basis which should underly the notion of agency has remained strikingly underdeveloped. This paper is intended to improve on this situation, by analysing the most basic notions necessary for a theory of agency: action, self, control, autonomy and adaptivity. Our main thesis is that autonomy is the essential concept in agency and that autonomy implies adaptivity. We supply a description of an adaptive autonomous agent (A3), based on the outlines given by Ashby [3]. Furthermore, we indicate how the two-folded adaptive powers, i.e. regulation and learning can be merged into one Reinforcement Learning (RL) system. We describe our RL implementation, which solves the as yet unexplored problem of dynamic goal state attainment.