| Abstract |
The field of Evolutionary Robotics aims to create robotic controllers with Evolutionary Algorithms. These algorithms are inspired by Darwin’s theory of survival of the fittest. In nature, animals survive and procreate when they are more fit. Similarly, a robotic controller is tested by observing the behaviour of the robot and is given a corresponding fitness measure. The higher the fitness, the more chance this controller has to procreate. Evolving robotic controllers can take a lot time. I investigate a possible way to reduce the learning time by using more robots that share knowledge. Sharing of knowledge results in an increased performance and reduces the learning time. |