How to write python code for policy iteration such that each state have different action?

Viewed 9

I'm working on python code for policy iteration and Q learning with grid world such that each state (the number of states is 9) has a different action. I have to define the action for each state. However, if I have a large number of states (such as 50), the method that defines each state's action may not be a good choice. Is there a better method to define the action for each state if we have a large number of states (such as 50)?

0 Answers
Related