Week 5-6. Simple Q learning - completed

For today I wanted to show a video with a small demonstration of how the implemented algorithm has managed to solve the problem. It should be noted that the video is uploaded to the platform with a playback speed three times higher than the original, as the car was driving at a very slow speed. Because of this, the car was able to follow the line with very little error, but it took forever to complete the circuit. In the video you can see how the algorithm is confronted with different situations on the track, in this case curves of different radius and straights. For the next post I would like to present an image where I explain better the reward function used to achieve this milestone.