A Study on Evolutionary Synthesis of Classifier System Architectures.
暂无分享,去创建一个
This paper describes a general method to design architectures of reinforcement learning systems. The task of these systems is to create a stimulus-response pattern by which the expected longterm total reward is maximized. Reinforcement learning systems have high applicability to a broad task class of autonomous agents because of their flexibility and autonomy. However, it is difficult to determine the relevant set of learning parameters for a given task. These parameters dominate the system architecture and largely affect the learning performance. Therefore, we propose a new approach involving evolutionary synthesis of simple classifier system architectures, which is known as a genetics-based machine learning system. This synthesis mechanism is realized using genetic algorithms. To examine the validity of our proposed method, the evolutionary synthesis technique is applied to motion planning tasks of a robot manipulator. Results from computer simulation indicate the usefulness of this approach.