Chuan-shanjia

您好，我有问题想请教一下。我感觉PPO相比于重要性采样的唯一区别是在约束中增加了一个约束项，使得$theta^'$与$theta$相差不大，为什么重要性采样是异策略，PPO是同策略呢？文章中说原因是PPO中$thete^'$是$theta_old$，但我觉得重要性采样中的$thete^'$也应该是$theta_old$呀。谢谢！

Hi, @CurryYuan , Did you meet the error https://github.com/daveredrum/D3Net/issues/5#issue-1594636475 ? I met a similiar error using the [checkpoint](https://www.dropbox.com/s/nsrbcfeihmh2bhw/D3Net.7z?dl=0): Traceback (most recent call last): File "scripts/eval.py", line 522, in model =...