chauncygu/Multi-Agent-Constrained-Policy-Optimisation

Mismatch between code and paper

BenfenYU opened this issue · 1 comments

Hi, thanks for your excellent job. I find a mismatch between code and paper about V-value network. As follows,
In paper:
image

In code:
image

Will different ways of using V-value network have a great impact on the experimental results? Thank you!

Hi, Thanks for comments, we have revised the algorithm, it should be global, by using concate()