Jie Liu

3s5z in PyMARL can quickly reached to win_rate of 1 and where is the config for SMAC of malib?

2

Thanks for this nice repo. I'm interested in MARL for smac. I have some problem about this repo. 1. In the page 18 of your [arxiv paper](https://arxiv.org/pdf/2106.07551.pdf), you mentioned that...

### How to use multi gpu? The most time-consuming part of the code is the load part of the data set, and I want to use multiple GPUs to speed...

how to deal with depthwise conv

5

Thanks for the great work. I want to use EKFAC to train MobileNet. However, it has depthwise conv whose groups is not equal to 1. How to implement it?

Troubleshooting OpenChat and Non-English Data in the Dataset

1

Great job! I have a few questions: 1. I'm using the following script to test OpenChat, but even with the correct prompt template, the output is not very accurate. How...

Different offlineRL papers use different versions of D4RL. Therefore the results of the same algorithm are inconsistent in different papers. The authors also needs to explain why the results are...

This issue is a collection of various interesting agent demonstrations trained by ACE, it will be updated continually. ### SMAC https://user-images.githubusercontent.com/37578514/206089013-4753c031-41fd-4b13-b429-0c02870246a2.mp4 We carefully analyze the behavior of transferred agents. As...

RuntimeError: CUDA error: unspecified launch failure

1

Hi, Thanks for your work. I want to reproduce the training process of the Premise Retriever. There are no issues during training, but there is a bug during testing. I...