tf_agents/agents/cql/cql_sac_agent.py [752:771]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
      critic_loss1 = td_errors_loss_fn(td_targets, pred_td_targets1)
      critic_loss2 = td_errors_loss_fn(td_targets, pred_td_targets2)
      critic_loss = critic_loss1 + critic_loss2

      if critic_loss.shape.rank > 1:
        # Sum over the time dimension.
        critic_loss = tf.reduce_sum(
            critic_loss, axis=range(1, critic_loss.shape.rank))

      agg_loss = common.aggregate_losses(
          per_example_loss=critic_loss,
          sample_weight=weights,
          regularization_loss=(self._critic_network_1.losses +
                               self._critic_network_2.losses))
      critic_loss = agg_loss.total_loss

      self._critic_loss_debug_summaries(td_targets, pred_td_targets1,
                                        pred_td_targets2)

      return critic_loss
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tf_agents/agents/sac/sac_agent.py [549:568]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
      critic_loss1 = td_errors_loss_fn(td_targets, pred_td_targets1)
      critic_loss2 = td_errors_loss_fn(td_targets, pred_td_targets2)
      critic_loss = critic_loss1 + critic_loss2

      if critic_loss.shape.rank > 1:
        # Sum over the time dimension.
        critic_loss = tf.reduce_sum(
            critic_loss, axis=range(1, critic_loss.shape.rank))

      agg_loss = common.aggregate_losses(
          per_example_loss=critic_loss,
          sample_weight=weights,
          regularization_loss=(self._critic_network_1.losses +
                               self._critic_network_2.losses))
      critic_loss = agg_loss.total_loss

      self._critic_loss_debug_summaries(td_targets, pred_td_targets1,
                                        pred_td_targets2)

      return critic_loss
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -