Competition_3v3snakes

Competition_3v3snakes copied to clipboard

A bug will lead to a failed greedy policy 训练代码有一个bug会使得greedy策略失效

1

我们在使用该仓库代码`rl_trainer/main.py`进行我们模型的训练时，发现了一个代码中的bug We have found a bug when we are using your code `rl_trainer/main.py` to train our own model ```python # …… 58-66 state_to_training = state[0] # you have defined state_to_training...

COMoER

Competition_3v3snakes/rl_trainer/common.py Line 11 device = torch.device("cuda:1") if torch.cuda.is_available() else torch.device("cpu") "cuda:1" should be replcaed by "cuda:0", or there is an error "CUDA error: invalid device ordinal" Because "cuda:1" chooses the...

fanqiNO1