agents/ql_cvae.py [158:168]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                target_q1, target_q2 = self.critic_target(next_state_rpt, next_action_rpt)
                target_q1 = target_q1.view(batch_size, 10).max(dim=1, keepdim=True)[0]
                target_q2 = target_q2.view(batch_size, 10).max(dim=1, keepdim=True)[0]
                target_q = torch.min(target_q1, target_q2)
            target_q = (reward + not_done * self.discount * target_q).detach()

            critic_loss = F.mse_loss(current_q1, target_q) + F.mse_loss(current_q2, target_q)

            self.critic_optimizer.zero_grad()
            critic_loss.backward()
            self.critic_optimizer.step()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



agents/ql_diffusion.py [122:132]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                target_q1, target_q2 = self.critic_target(next_state_rpt, next_action_rpt)
                target_q1 = target_q1.view(batch_size, 10).max(dim=1, keepdim=True)[0]
                target_q2 = target_q2.view(batch_size, 10).max(dim=1, keepdim=True)[0]
                target_q = torch.min(target_q1, target_q2)
            target_q = (reward + not_done * self.discount * target_q).detach()

            critic_loss = F.mse_loss(current_q1, target_q) + F.mse_loss(current_q2, target_q)

            self.critic_optimizer.zero_grad()
            critic_loss.backward()
            self.critic_optimizer.step()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -