Reinforcement-learning-with-PyTorch

Reinforcement-learning-with-PyTorch copied to clipboard

RuntimeError about AC_CartPole.py

8

I didn't change anything about `8_Actor_Critic_Advantage/AC_CartPole.py`. I just ran it, but I got this ``` RuntimeError: one of the variables needed for gradient computation has been modified by an inplace...

Coder-Liuu

5_Deep_Q_Network中RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead.

3

RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead.增加了detach()也一样报错，输出loss图异常

NikoHsu

Using tensorboard to show graph of DQN

1

在莫烦的网课里使用了 tensorboard来展示网络结构，想请教一下pytorch如何使用tensorboard来展示网络结构（看过很多教程，都是在add_graph方法中传入module，但DQN类并不是一个module，而是由两个module组成的，所以想请教一下有无解决方案）

jzndd