Genetic algorithms

We have tried out Q-learning in a couple of different configurations, with a limited amount of success in training our robot.  The main problem with Q-learning is that we have a very large number of possible states, or positions, that the robot arm can be in.  This means that gaining a lot of knowledge about any one position by repeated trials is very difficult.  We are going to introduce a different approach using genetic algorithms to generate our movement actions. 

Moving the robot arm requires coordination of three motors simultaneously to create a smooth movement.  We need a mechanism to create different combinations of motor movement for the robot to test.  We could just use random numbers, but that is inefficient, ...

Get Artificial Intelligence for Robotics now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.