Deterministic behavior was enabled with either `torch.use_deterministic_algorith...

✗ 实验 123_2 失败: Deterministic behavior was enabled with either `torch.use_deterministic_algorithms(True)` or `at::Context::setDeterministicAlgorithms(true)`, but this operation is not deterministic because it uses CuBLAS and you have CUDA >= 10.2. To enable deterministic behavior in this case, you must set an environment variable before running your PyTorch application: CUBLAS_WORKSPACE_CONFIG=:4096:8 or CUBLAS_WORKSPACE_CONFIG=:16:8. For more information, go to https://docs.nvidia.com/cuda/cublas/index.html#results-reproducibility Traceback (most recent call last): File "c:\Users\98317\Downloads\DRL_Humanoidv5_SAC_super\run0.py", line 129, in run_single_experiment main_module.train_sac_with_config(config) File "c:\Users\98317\Downloads\DRL_Humanoidv5_SAC_super\main_withoutdropout.py", line 717, in train_sac_with_config train_sac(config) File "c:\Users\98317\Downloads\DRL_Humanoidv5_SAC_super\main_withoutdropout.py", line 630, in train_sac losses = agent.update(data) ^^^^^^^^^^^^^^^^^^ File "c:\Users\98317\Downloads\DRL_Humanoidv5_SAC_super\main_withoutdropout.py", line 456, in update qf1_next_target = self.forward_q1_target(next_observations, next_state_actions) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\98317\.conda\envs\UnoReverse\Lib\site-packages\torch\nn\modules\module.py", line 1775, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\98317\.conda\envs\UnoReverse\Lib\site-packages\torch\nn\modules\module.py", line 1786, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "c:\Users\98317\Downloads\DRL_Humanoidv5_SAC_super\main_withoutdropout.py", line 43, in forward x = self.fc3(x) ^^^^^^^^^^^ File "C:\Users\98317\.conda\envs\UnoReverse\Lib\site-packages\torch\nn\modules\module.py", line 1775, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\98317\.conda\envs\UnoReverse\Lib\site-packages\torch\nn\modules\module.py", line 1786, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\98317\.conda\envs\UnoReverse\Lib\site-packages\torch\nn\modules\linear.py", line 134, in forward return F.linear(input, self.weight, self.bias) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: Deterministic behavior was enabled with either `torch.use_deterministic_algorithms(True)` or `at::Context::setDeterministicAlgorithms(true)`, but this operation is not deterministic because it uses CuBLAS and you have CUDA >= 10.2. To enable deterministic behavior in this case, you must set an environment variable before running your PyTorch application: CUBLAS_WORKSPACE_CONFIG=:4096:8 or CUBLAS_WORKSPACE_CONFIG=:16:8. For more information, go to https://docs.nvidia.com/cuda/cublas/index.html#results-reproducibility