Nathan Lambert

I would be interested in contributing @luisenp. Long time been on my list to study it.

I'm here to say that I'm shocked that they changes the `env.step()` API. A bit of a weird one, I wonder if there's a `kwarg` for keeping it the same,...

Yes, I have a version of this in my private repo, I will create a PR soon for it. The way I did it was for associating a "weight" for...

Related comment, I think it may be worthwhile to have an optional "rich logging" mode, where things like candidate actions, action sequences (plans) at each step, trajectories, and more are...

Torch has a `vmap`??? !!!

A set of scalars (can almost use the input normalizers) that map from the raw network outputs to the actual states of the environment. Two times this was useful: 1....

@luisenp do you know with the current replay buffer trajectory storing, if at training time it will be easy to get the "trajectory time index" corresponding to the step of...

Also, I'm not sure what to do with `pre-commits`, they're failing because I am using a different version of python I think? ``` gi[INFO] Installing environment for https://github.com/psf/black. [INFO] Once...

@robertocalandra @albertwilcox may be interested.

I really like the sounds of that, let me try and make those additions. It removes complexity in a way that I think is fitting.