Nikhil Bhattasali

> Wow, this PR looks good. The main feedback I have is that we don't actually yet have any algorithms implemented in PyTorch that can train an RNN. Unfortunately, our...

@ryanjulian @richardliaw Would love to use garage with automatic hyperparameter tuning like ray-tune! Is there a draft of this doc or an existing repo that exemplifies how this can be...

It would be helpful if someone familiar with garage could explain how Ray currently is being used. As I referred to above, running a trainer prints "View the Ray dashboard...

Thanks, that makes sense! I'll play around with it.

One requirement of `ray.tune` is that you `tune.report` the performance metric(s) each epoch so the search algorithm can evaluate hyperparameter combinations and terminate bad performing ones early. Is there a...

> I'm planning to implement the followings to add RNN support to PPO/ TRPO: > > * [x] RNN: `lstm_module` > * [x] RNN policies and its module for PPO:...

Yes, this seems like a mistake. Until it's fixed, this hack worked for me: ``` // In Typography constructor: overrideStyles: () => ({ 'td,th': { textAlign: null, }, // ......

For easy reference, the "hammock.xml"/"humanoid_body.xml" mentioned: https://github.com/deepmind/mujoco/tree/main/model/hammock @Balint-H: My problem is that even though the `` format in your "hammock.xml" example works and is **necessary** when testing in "mujoco.viewer", once...

Resolved in https://github.com/facebookincubator/submitit/issues/1677.