Zichao Yang

the padding for dilated convolution seems to be wrong

7

For encoder, the dilated convolution for encoder pads ``` (filter_width - 1) * dilation/2```, this means after reshaping there are ```(filter_width-1)``` zeros at the beginning. But ```conv1d``` uses ```SAME``` padding,...

can not reproduce experiment shown in figure

2

Hi, can you share a configuration that can reproduce the results you showed on the figure? I run the default M1 configuration and only get average episodic reward at around...

_solve_adjoint_derivative_dense much slower than np.linalg.solve

2

`diffcp` is installed with openmp flags: ` MARCH_NATIVE=1 OPENMP_FLAG="-fopenmp" pip install diffcp ` It's at least 5 times slower than `np.linalg.solve`. Eigen solve should not be much slower than np.linalg.solve....