Daniel Perazzo

I just create a drive with the [results](https://drive.google.com/drive/folders/1vtwwgFEw4SP8yYBbyv0hjlM3oJCrLlxK?usp=sharing) that I got. It seems strange because, the thing that I did was perform the fine-tuning as instructed by the paper. Did...

Oksay, thank you!

hello @seba-1511, thanks! I have been trying to use learn2learn on a problem, does your team plan on supporting this functionality in the future? And are there any examples of...

Hello @Pathi-rao, actually I did not use the `l2l.data.MetaDataset`, I just used the standard dataet loader on my problem and it seems to work just fine.

Hello everyone, I have the same problem, but on WIndows

I got the same problem. And also this message appeared: `touch: cannot touch 'shared/training_exited': No such file or directory touch: cannot touch 'shared/training_exited'`

1. Operating System: Ubuntu 20.04 2. Command which I ran: `bash utility/train_locally.sh --verbose` 3. Output log: > /home/daniel/anaconda3/envs/minerl/lib/python3.7/site-packages/gym/logger.py:30: UserWarning: WARN: Box bound precision lowered by casting to float32 warnings.warn(colorize('%s: %s'%('WARN',...

As @Miffyli said, just doing `sudo apt install xvfb` worked for me

Hello @hongsukchoi, I think I managed to reproduce it, or at least got close to it. I trained in the default setting (only with the batch size reduced by 2...

Hello @HexagonPrime, I have the exact same configuration as yours. I decreased the batch size to 2 instead of 4 and it is now training in the DTU dataset