dqn.py 文件源码

def _compute_loss(self, exp_batch, gamma, errors_out=None):
        """Compute the Q-learning loss for a batch of experiences


        Args:
          experiences (list): see update()'s docstring
          gamma (float): discount factor
        Returns:
          loss
        """

        y, t = self._compute_y_and_t(exp_batch, gamma)

        if errors_out is not None:
            del errors_out[:]
            delta = F.sum(abs(y - t), axis=1)
            delta = cuda.to_cpu(delta.data)
            for e in delta:
                errors_out.append(e)

        if 'weights' in exp_batch:
            return compute_weighted_value_loss(
                y, t, exp_batch['weights'],
                clip_delta=self.clip_delta,
                batch_accumulator=self.batch_accumulator)
        else:
            return compute_value_loss(y, t, clip_delta=self.clip_delta,
                                      batch_accumulator=self.batch_accumulator)