Reinforcement Learning Trees

Two new reinforcement learning algorithms are presented. Both use a binary tree to store simple local models in the leaf nodes and coarser global models towards the root. It is demonstrated that a meaningful partitioning into local models can only be accomplished in a fused space consisting of both input and output. The first algorithm uses a batch like statistic procedure to estimate the reward functions in the fused space. The second one uses channel coding to represent the output- and input vectors allowing a simple iterative algorithm based on competing subsystems. The behaviors of both algorithms are illustrated in a preliminary experiment. 1 INTRODUCTION The aim with our research is to develop efficient learning algorithms for autonomous systems (e.g. robots). Such a system is supposed to act in a closed loop with its environment, i.e. the system's output will influence its input. In this case a supervised learning algorithm would not be very useful since it would be impossible ..