[2025-10-11 20:55:32,238][py.warnings][WARNING] - C:\Users\wuzhe\anaconda3\envs\drl_hw2\lib\site-packages\torch\cuda\__init__.py:283: UserWarning: 
    Found GPU0 NVIDIA GeForce RTX 5090 which is of cuda capability 12.0.
    Minimum and Maximum cuda capability supported by this version of PyTorch is
    (6.1) - (9.0)
    
  warnings.warn(

[2025-10-11 20:55:32,238][py.warnings][WARNING] - C:\Users\wuzhe\anaconda3\envs\drl_hw2\lib\site-packages\torch\cuda\__init__.py:304: UserWarning: 
    Please install PyTorch with a following CUDA
    configurations:  12.8 12.9 following instructions at
    https://pytorch.org/get-started/locally/
    
  warnings.warn(matched_cuda_warn.format(matched_arches))

[2025-10-11 20:55:32,240][py.warnings][WARNING] - C:\Users\wuzhe\anaconda3\envs\drl_hw2\lib\site-packages\torch\cuda\__init__.py:326: UserWarning: 
NVIDIA GeForce RTX 5090 with CUDA capability sm_120 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_61 sm_70 sm_75 sm_80 sm_86 sm_90.
If you want to use the NVIDIA GeForce RTX 5090 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/

  warnings.warn(

[2025-10-11 20:55:33,876][__main__][INFO] - Training for 50000 timesteps with NormalQNetwork and NormalReplayBuffer