-
From the end of section 3 in the GAE paper: **High-Dimensional Continuous Control Using Generalized Advantage Estimation**
https://arxiv.org/pdf/1506.02438.pdf
```
Taking γ < 1 introduces bias in…
-
Hi
Is there any reason that env.reset() [during training for A2C] was not called at the end of each rollout()? It only called one time https://github.com/ikostrikov/pytorch-a2c-ppo-acktr/blob/master/…
-
上周:
~找出了那个网络一直训练但是感觉参数没有变得真正原因,不是reward太发散了,而是梯度并没有共享,真是煞笔,不过750ti训练真是慢。
~巩固了一点点有关gan的知识,觉得gan还是挺好玩的。
下周:
~虽然换了个更高级的显卡,但感觉这样下去还是没办法快速收敛,所以我是想先加个discriminator做成gan的样子,然后用一些低级的算法产生一些数据,然后再去找专家棋局的dat…
-
Hello !
I find your code is old version wihth Pytorch and I update which refer [ikostrikov/pytorch-a3c](https://github.com/ikostrikov/pytorch-a3c).
I want ask this repositories is work to doom …
-
Great work on this project so far, looks really promising.
In trying to replicate model training, I have noticed the following error:
Traceback (most recent call last):
File "main.py", line 1…
-
### System information
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**: Linux Ubuntu 16.04
- **Ray installed from (source or binary)**: source
- **Ray version**: 0.5.3
- **Python…
-
The following test failure has been very common in Jenkins recently. E.g., https://amplab.cs.berkeley.edu/jenkins/job/Ray-PRB/10597/console.
```
+ docker run --rm --shm-size=20G --memory=20G 807ab…
-
macOS 10.13.4
Python 3.6.4
pytorch 0.4.0
I encountered an error
```
~/py-garage/pytorch-a3c(master*) » python3 main.py --env-name "PongDeterministic-v4" --num-processes 1 …
-
I can't run the 01_a3c_data.py and 02_a3c_grad.py file in chapter11 on windows.
I get this error:
`
THCudaCheck FAIL file=c:\users\administrator\downloads\new-builder\win-
wheel\pytorch…
-
Hi, Morvan,
In your `push_and_pull` function, you update the `global grad` without any condition, see https://github.com/MorvanZhou/pytorch-A3C/blob/master/discrete_A3C.py#L95. However, for other i…