Deep Reinforcement Learning (DRL) connects the classic Reinforcement Learning algorithms with Convolutional Neuronal Networks (CNN). The problem in DRL is that it is not easy to understand what the CNN is learning. In order to be able to use the programs in highly dangerous environments for humans and machines, the developer need a debugging tool to improve that the program does what he expects.
The aim of this Master's Thesis is to bring some of the best-known visualization methods from the field of image classification to the area of Deep Reinforcement Learning (DRL). To improve how far they can be used in the area of Reinforcement learning and to compare them. Furthermore, the question also arises how well the different DRL algorithms can be visualized if at all.
