A case study on learning a steering controller from scratch with reinforcement learning
Martin Lauer · 2011
In this case study we show how reinforcement learning can be applied successfully for low level control tasks in autonomous driving like steering control as an alternative to controllers from classical control theory. We describe the learning procedure and compare the resulting control policies with a classical controller. The experiments are made both in simulation and on a real car and we discuss the case of driving forwards as well as of driving backwards.