Method get

examples/reinforcement_learning/tutorial_TRPO.py:160–172

Call this at the end of an epoch to get all of the data from the buffer, with advantages appropriately normalized (shifted to have mean zero and std one). Also, resets some pointers in the buffer.

(self)

        return self.ptr == self.max_size

    def get(self):
        """
        Call this at the end of an epoch to get all of the data from
        the buffer, with advantages appropriately normalized (shifted to have
        mean zero and std one). Also, resets some pointers in the buffer.
        """
        assert self.ptr == self.max_size  # buffer has to be full before you can get
        self.ptr, self.path_start_idx = 0, 0

        # the next two lines implement the advantage normalization trick
        adv_mean, adv_std = np.mean(self.adv_buf), np.std(self.adv_buf)
        self.adv_buf = (self.adv_buf - adv_mean) / adv_std
        return [self.obs_buf, self.act_buf, self.adv_buf, self.ret_buf, self.logp_buf, self.mean_buf, self.log_std_buf]


"""