Open mitchross opened 5 years ago
I meet the question so. It cause bytorch version. In latest torch, 0-dim tensor is invaild, 我也遇到这问题,是torch版本引起的,稍作修改即可。
Change code line77
action = torch.argmax(prediction)[0]
To
action = torch.argmax(prediction)
I tried that. Still errors
(python36) C:\Flappy-bird-deep-Q-learning-pytorch>python train.py
Traceback (most recent call last):
File "train.py", line 15, in
@2448845600 thanks, guy! fix my problem.
@2448845600 谢谢~搞定啦
Flappy-bird-deep-Q-learning-pytorch/src/deep_qnetwork.py:21: UserWarning: nn.init.uniform is now deprecated in favor of nn.init.uniform. nn.init.uniform(m.weight, -0.01, 0.01) Perform a random action Iteration: 2/2000000, Action: 1, Loss: 0.010123813524842262, Epsilon 0.1, Reward: 0.1, Q-value: 0.0005683371564373374 Traceback (most recent call last): File "train.py", line 133, in
train(opt)
File "train.py", line 74, in train
action = torch.argmax(prediction)[0]
IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number
(python36) bash-3.2$