Dear students,
We release a coding exercise for you to get hands-on experience with the Q-table update rules we learned in the class. Your task is to escape a simple maze as fast as possible.
We provide you a Jupyter notebook and you will code in Python. You do not need to install any other package than numpy. You will not submit this micro-project for grading, but it will be useful especially if you want to do the (deep) Reinforcement Learning (RL) mini-project later on.
Hope you have fun!
the TA team