Abstract

This paper reviews progress in Deep Learning and the successful Application of Deep Q Networks to Competitive Games. The basis of the method is Watkins' Deferred Rewards Learning[1]. However its implementation in its current form is due to D. Hassabis et al [2]. In its current form the technology is heavily dependent on image processing. This suggests that the method may be adapted for the establish ment of Optimal Maintenance Policies for Complex systems such as Airliners and/or racing cars with the addition of monitoring of Sound.