Exploring the concept of Reinforcement Learning with the Q-Learning algorithm in my blog: https://www.ontdeksels.nl/ontdeksel-11-de-kunstmatige-intelligentie-van-cpn-jesse/ (Dutch).
In this small 'game' you can place:
- the start
- some obstacles
- the finish
in a 7x7 grid. The algoritm will then search for the best route with the Q-learning algorithm. Speed is adjustable.
https://www.freepik.com/free-vector/pirate-icons-set-flat_3976520.htm#index=1