Bewertendes Lernen optimaler Bremspunkte in Kurvenfahrten


This work shows a way to implement an agent, capable to learn to drive a given track with a high speed. To illustrate the need of a machine learning technique, the physics and the complexity of driving a turn are shown. After this there is a description of the design and im- plementation for a a reinforcement learning algorithm with a continuous state-action-space. There are several references to the requirements of the FAUST platform.