Elapsedf
commented
4 months ago Oh, I have solved it with this blog: https://blog.csdn.net/a563562675/article/details/121656894 I would closed the issue :)
Closed Elapsedf closed 4 months ago
Elapsedf
commented
4 months ago Oh, I have solved it with this blog: https://blog.csdn.net/a563562675/article/details/121656894 I would closed the issue :)
Thank you very much for opening up the repo! However, when I run the code "python run_mappo.py", it raise an error as below: ❯ python run_mappo.py /data/shenzhen/anaconda3/envs/marl_cav/lib/python3.6/site-packages/torch/cuda/init.py:104: UserWarning: NVIDIA GeForce RTX 3090 with CUDA capability sm_86 is not compatible with the current PyTorch installation. The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_70 sm_75. If you want to use the NVIDIA GeForce RTX 3090 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/
warnings.warn(incompatible_device_warn.format(device_name, capability, " ".join(arch_list), device_name)) ERROR:root:Can not find checkpoint for ./results/Jul_15_08_19_29/models/ Traceback (most recent call last): File "run_mappo.py", line 227, in
train(args)
File "run_mappo.py", line 133, in train
mappo.interact()
File "/data/shenzhen/zdf/Highway/MARL_CAVs/MARL/MAPPO.py", line 113, in interact
action = self.exploration_action(self.env_state, self.n_agents)
File "/data/shenzhen/zdf/Highway/MARL_CAVs/MARL/MAPPO.py", line 219, in exploration_action
softmax_actions = self._softmax_action(state, n_agents)
File "/data/shenzhen/zdf/Highway/MARL_CAVs/MARL/MAPPO.py", line 209, in _softmax_action
softmax_action_var = th.exp(self.actor(state_var[:, agent_id, :]))
File "/data/shenzhen/zdf/Highway/MARL_CAVs/MARL/single_agent/Model_common.py", line 19, in call
out = nn.functional.relu(self.fc1(state))
File "/data/shenzhen/anaconda3/envs/marl_cav/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/data/shenzhen/anaconda3/envs/marl_cav/lib/python3.6/site-packages/torch/nn/modules/linear.py", line 93, in forward
return F.linear(input, self.weight, self.bias)
File "/data/shenzhen/anaconda3/envs/marl_cav/lib/python3.6/site-packages/torch/nn/functional.py", line 1690, in linear
ret = torch.addmm(bias, input, weight.t())
RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling
cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)I have checked the closed issue and don't find the same solved issue. So I would appreciate it if you could help me :)