Closed yexm-ze closed 6 years ago
The error was solved by change all instances of relu to tanh,I don't know why, but it worked. https://github.com/agakshat/maddpg/issues/5
Hi, I am experiencing the same problem when training in the simple_spread scenario, but I do not feel like changing the activation functions is the way to go... Can we re-open this issue?
Thanks
@camigord ,Maybe you can refer to this implementation:https://github.com/shariqiqbal2810/maddpg-pytorch. It adds a BN layer,and change the activation functions according to different situations.
Hello, when I run your code, everything seems to be fine. But when I display the result after 60000 episodes, the agent flashes quickly and disappears quickly. I printed the reward and action, at a certain time, probably after 1500 episodes, they become nan, I didn't change anything and what to know why, maybe you can give me some advice, thank you !![image](https://user-images.githubusercontent.com/15141243/37448911-4675798c-2863-11e8-9b5d-5126f7a8c13b.png)