Implementing an agent to perform autonomous driving

Now that you have seen RL working in progressively challenging environments, we will conclude this chapter by demonstrating that the same concepts can be applied to a self-driving car. Since it is impractical to see this working on an actual car, we will resort to a simulated environment. The environment is going to be a full-fledged city of traffic, with cars and additional details within the image of a road. The actor (agent) is a car. The inputs to the car are going to be various sensory inputs such as a dashcam, Light Detection And Ranging (LIDAR) sensors, and GPS coordinates. The outputs are going to be how fast/slow the car will move, along with the level of steering. This simulation will attempt to be an accurate representation of real-world physics. Thus, note that the fundamentals will remain the same, whether it is a car simulation or a real car.

Note that the environment we are going to install needs a graphical user interface...