A Binary Competition Tree for Reinforcement Learning

A robust, general and computationally simple reinforcement learning system is presented. It uses channel a representation which is robust and continuous. The accumulated knowledge is represented as a reward prediction function in the outer product space of the inputand output channel vectors. Each computational unit generates an output simply by a vector-matrix multiplication and the response can therefore be calculated fast. The response and a prediction of the reward are calculated simultaneously by the same system, which makes TD-methods easy to implement if needed. Several units can cooperate to solve more complicated problems. A dynamic tree structure of linear units is grown in order to divide the knowledge space into a su ciently number of regions in which the reward function can be properly described. The tree continuously tests splitand prune criteria in order to adapt its size to the complexity of the problem.