RandomSampler.py

class RandomSampler(BaseSampler):
    def __init__(self, env):
        super().__init__(env)
        
    def choose_k(self):
        
        self.k = np.random.choice(self.variants)
        
        return self.k
    
    def update(self):
        # nothing to update
        self.thetaregret[self.i] = np.max(self.theta) - self.theta[self.k]
        
        self.a[self.k] += self.reward
        self.b[self.k] += 1
        self.theta = self.a/self.b

        self.ad_i[self.i] = self.k
        self.r_i[self.i] = self.reward
        self.i += 1