Swap Loss not Decreasing in Contrastive Learning

[P1terQ]

In the paper, the authors highlight that using contrastive learning can carry more precious environmental information, and the t-SNE visualization indicates the stronger representation ability of this method.

However, when I attempted to run the open-source code, the swap loss didn't drop, regardless of short or long iterations.

I am wondering if this is an expected behavior for contrastive learning algorithms, or if there might be an issue with my implementation.

[kc-ustc]

Thanks for your sharing! I have met the same problms about swap loss.And I also try ablation study without contrastive learning by setting swap loss = 0,finding that the linear velocity tracking reward during training seems to make no difference with original version.