algorithms.py 文件源码

def run(self,T,model):
        self.trials = np.zeros(model.K)
        self.success = np.zeros(model.K)
        for t in xrange(T):
            x,y = model.sample(model.K-1)
            xij = np.hstack((1-x,x,1)) # first N actions represent x_i = 0,2nd N x_i=1, last do()
            self.trials += xij
            self.success += y*xij
        self.u = np.true_divide(self.success,self.trials)
        self.best_action = argmax_rand(self.u)
        return max(model.expected_rewards) - model.expected_rewards[self.best_action]