Supervised Reinforcement Learning

Revision with unchanged content. Can machines be taught? If so, what methods are useful for teaching machines? Machine learning is a field focused on systems that can learn through their own experiences and evaluation. Programmers could encode all behaviors for a task, but this process quickly becomes limited to condensed problems. Therefore, scientists have turned to methods with adaptability, ta­king cues from biological systems (including the human brain) to solve more complex problems in varied environments. This book describes two experi­ments implementing supervised reinforcement learning on a real, mobile ro­bot. One tests the robot's reliability in completing a navigation task it has been taught by a supervisor. The other, in which obstacles are placed along the path to the goal, measures the robot's robustness to changes in environ­ment. Experimental analysis answered: How quickly can the robot find the goal? How much reward does the robot amass? How often does the robot fail in the task? How closely does the robot match the supervisor's actions? This book is addressed to those looking for means to teach robots about rewards/punishments, such as researchers in Robotics, Machine Learning, and Engineering.