policies.py 文件源码

def update_policy(self, ob_no, ac_n, std_adv_n, stepsize):
        """ 
        The input is the same for the discrete control case, except we return a
        single log standard deviation vector in addition to our logits. In this
        case, the logits are really the mean vector of Gaussians, which differs
        among components (observations) in the minbatch. We return the *old*
        ones since they are assigned, then `self.update_op` runs, which makes
        them outdated.
        """
        feed = {self.ob_no: ob_no,
                self.ac_na: ac_n,
                self.adv_n: std_adv_n,
                self.stepsize: stepsize}
        _, surr_loss, oldmean_na, oldlogstd_a = self.sess.run(
                [self.update_op, self.surr_loss, self.mean_na, self.logstd_a],
                feed_dict=feed)
        return surr_loss, oldmean_na, oldlogstd_a