Narsil-Dinghuai Zhang 张鼎怀
Narsil-Dinghuai Zhang 张鼎怀
**Describe the bug** I have R Studio in my mac and have installed packages in [https://github.com/FenTechSolutions/CausalDiscoveryToolbox/blob/master/r_requirements.txt](https://github.com/FenTechSolutions/CausalDiscoveryToolbox/blob/master/r_requirements.txt). But I still get `ImportError: R Package bnlearn is not available.` when running `GS()`...
I am a student who is reading ESL currently. I think this repo is more readable than the book, while there're many typos in this repo. May I open some...
I would like to write a wrapper for dm control environment and zero out some specific dimensions of the state. But I don't know the detailed physical meaning (i.e., position...
In VAT paper the hyperparameter xi is set to `1e-6` (only a small value coincides with taylor expansion), why in this repo it is `10`?
I adjust learning rate according to the author, however, I can only get a test accuracy of 93%. I didn't normalize when preprocessing dataset, which may be the cause. But...
In https://github.com/denisyarats/exorl/blob/main/custom_dmc_tasks/point_mass_maze.py#L155, why there are the following modifications over the original dmc [point_mass](https://github.com/deepmind/dm_control/blob/main/dm_control/suite/point_mass.py#L71) environment? `physics.data.qpos[0] = np.random.uniform(-0.29, -0.15)` `physics.data.qpos[1] = np.random.uniform(0.15, 0.29)` `physics.named.data.geom_xpos['target'][:] = self._target`