What if we need to decide multiple times with uncertainty and with decisions influencing our future decisions?
+ α,β exercise solution
Navigating through a gridworld and calculating the proper path.
+ exercise from https://www.youtube.com/watch?v=DiWdWXfVhfs (Solution: https://www.youtube.com/watch?v=ZNKk5j52Db8)
Markov decision process. Try running mdp_sandbox.py and ask if something is not clear.