(self, td_estimate, td_target)
| 546 | self.loss_fn = torch.nn.SmoothL1Loss() |
| 547 | |
| 548 | def update_Q_online(self, td_estimate, td_target): |
| 549 | loss = self.loss_fn(td_estimate, td_target) |
| 550 | self.optimizer.zero_grad() |
| 551 | loss.backward() |
| 552 | self.optimizer.step() |
| 553 | return loss.item() |
| 554 | |
| 555 | def sync_Q_target(self): |
| 556 | self.net.target.load_state_dict(self.net.online.state_dict()) |