5 lines
645 B
Plaintext
5 lines
645 B
Plaintext
[2025-10-11 22:02:58,218][__main__][INFO] - Training for 50000 timesteps with NormalQNetwork and NormalReplayBuffer
|
|
[2025-10-11 22:02:58,512][py.warnings][WARNING] - d:\Documents\Nextcloud\Documents\Project WUSTL\Academic\2025_Fall\CSE5100\Homeworks\hw2\hw2\agent.py:56: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.detach().clone() or sourceTensor.detach().clone().requires_grad_(True), rather than torch.tensor(sourceTensor).
|
|
np.where(done, torch.tensor(reward).to(self.device), torch.tensor(reward).to(self.device) + torch.max(self.target_net(torch.tensor(next_state).to(self.device)))* self.gamma)
|
|
|