iuri frosio

Hi, cule is supposed to replace openai gym. Code in the examples folder show how to use cule for a2c, vtrace, dqn, and other typical RL algorithms. However, I believe...

If you want to move quick, can you try the docker image? That should work out of the box.

For docker instructions we posted: FROM nvidia/cuda:10.0-cudnn7-devel-ubuntu18.04 as base ... RUN pip install torch==1.2.0 It looks like you are using different CUDA / pytorch versions. Any particular reason for this...

We are discussing how/when/what to release exactly in these days. Please keep an eye on it.

Hi, I need to solve some copyright issue before releasing it. My hope is to finally reach the end of this in the next days. I. From: Haoyu Liu ***@***.***>...

Not immediately, but it shouldn't be hard to implement it in TF. If you have any version with LSTM, please let us know.

Never seen this. What environment are you using? Can you update the drivers?

GPU driver

$@ is all of the parameters passed to the script in the sh file. Please also double check that your config file contains correct parameters. It may be that your...

We are not planning implementing it for now, but some people are indeed suggesting that pyTorch may be faster than TF. It would be great if someone can implement GA3C...