Monte Carlo control
In the control task, our goal is to find the optimal policy. Unlike the prediction task, here, we will not be given any policy as an input. So, we will begin by initializing a random policy, and then we try to find the optimal policy iteratively. That is, we try to find an optimal policy that gives the maximum return. In this section, we will learn how to perform the control task to find the optimal policy using the Monte Carlo method.
Okay, we learned that in the control task our goal is to find the optimal policy. First, how can we compute a policy? We learned that the policy can be extracted from the Q function. That is, if we have a Q function, then we can extract policy by selecting an action in each state that has the maximum Q value as the following shows:
So, to compute a policy, we need to compute the Q function. But how can we compute the Q function? We can compute the Q function similarly to what we learned in the MC prediction method. That...