Reinforcement learning for robot control

摘要

Writing control code for mobile robots can be a very time-consuming process. Even for apparently simple tasks, it is often difficult to specify in detail how the robot should accomplish them. Robot control code is typically full of "magic numbers" that must be painstakingly set for each environment that the robot must operate in. The idea of having a robot learn how to accomplish a task, rather than being told explicitly is an appealing one. It seems easier and much more intuitive for the programmer to specify what the robot should be doing, and to let it learn the fine details of how to do it. In this paper, we describe JAQL, a framework for efficient learning on mobile robots, and present the results of using it to learn control policies for some simple tasks.