leao1995

question about DRQN

5

https://github.com/thu-ml/tianshou/blob/f13e415eb0de55baca5dc0d6fae39d6a38e8bc0b/tianshou/policy/modelfree/dqn.py#L167 It seems `state` is not used during training even when specifying a recurrent net. Am I missing something, or is it expected?

https://github.com/lilianweng/deep-reinforcement-learning-gym/blob/4fec4876ad28fe83309efd2cdf2a6f4281a5b23c/playground/policies/ddpg.py#L47 a is rescaled, but mu is not.

Is this a bug?

2

https://github.com/openai/glow/blob/eaff2177693a5d84a1cf8ae19e8e0441715b82f8/model.py#L552 this is equivalent to evaluate (z-mean)/scale on a standard Gaussian, but you didn't account for the determinant of this transformation.

Is it possible to support 3D convolution?

8

I want to use 3D version of deformable convolution, but it seems like your code only support 2D. What change should be made to adapt to 3D convolution? Is it...

Why do you freeze batch norm parameters when training?

4

would it be better to let batch norm parameters adapt to your current data?

https://github.com/OpenXAIProject/Joint-AFA-Classification/blob/55811e71376ed6d90a4f2012694cb3891ac48a56/environment.py#L87 should be len(np.where(...)[0]) here.