Trance-0/CSE5100H2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

done?

Browse Source
This commit is contained in:
Zheyuan Wu
2025-10-12 00:55:07 -05:00
commit 250f763f1f
467 changed files with 19784 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
runs/2025-10-11/22-09-31_/main.log Normal file
View File

@@ -0,0 +1,7 @@
[2025-10-11 22:09:33,607][__main__][INFO] - Training for 50000 timesteps with NormalQNetwork and NormalReplayBuffer
[2025-10-11 22:09:33,902][py.warnings][WARNING] - d:\Documents\Nextcloud\Documents\Project WUSTL\Academic\2025_Fall\CSE5100\Homeworks\hw2\hw2\agent.py:55: 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).
max_tensor = torch.max(self.target_net(torch.tensor(next_state).to(self.device)).cpu(), dim=1)
[2025-10-11 22:09:33,932][py.warnings][WARNING] - d:\Documents\Nextcloud\Documents\Project WUSTL\Academic\2025_Fall\CSE5100\Homeworks\hw2\hw2\agent.py:57: 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).
tensor_arr = np.where(done, torch.tensor(reward).to(self.device), torch.tensor(reward).to(self.device) + max_tensor * gamma_tensor)