Snippet for toyCarIRL, blog usage, not executable

toyCarIRL3.py

class irlAgent:
    def __init__(self, randomFE, expertFE, epsilon, num_states, num_frames, behavior):
        self.randomPolicy = randomFE
        self.expertPolicy = expertFE
        self.num_states = num_states
        self.num_frames = num_frames
        self.behavior = behavior
        self.epsilon = epsilon # termination when t < 0.1
        self.randomT = np.linalg.norm(np.asarray(self.expertPolicy)-np.asarray(self.randomPolicy)) #norm of the diff in expert and random
        self.policiesFE = {self.randomT:self.randomPolicy} # storing the policies and their respective t values in a dictionary
        print ("Expert - Random at the Start (t) :: " , self.randomT) 
        self.currentT = self.randomT
        self.minimumT = self.randomT