algorithms.py 文件源码

def run(self,T,model):
        self.trials = np.full(model.K,2,dtype=int)
        self.success = np.full(model.K,1,dtype=int)

        for t in xrange(T):
            fails = self.trials - self.success
            theta = np.random.beta(self.success,fails)
            arm = argmax_rand(theta)
            self.trials[arm] +=1
            self.success[arm]+= model.sample_multiple(arm,1)

        mu = np.true_divide(self.success,self.trials)
        self.best_action = argmax_rand(mu)
        return max(model.expected_rewards) - model.expected_rewards[self.best_action]