Huang Di

Maybe a bug in [class NT_Xent(nn.Module)](https://github.com/Spijkervet/SimCLR/blob/04bcf2baa1fb5631a0a636825aabe469865ad8a9/simclr/modules/nt_xent.py#L7) when using multi-gpus. The `mask` and `positive/negative pairs` are wrong I think.

Hi @Sanfee18, have you ever been able to train the ppo agent? I tried to use your code with minerlv1.0.1 but the reward remained zero for 110k steps. Or, have...

Thanks! I see.