Luis Pineda

It's via `functorch` which is a separate [library](https://github.com/pytorch/functorch) but I think they work closely with PyTorch's team.

Hi @mkolodziejczyk-piap. This is an interesting suggestion. Can you give a more concrete example to help me sketch out something? As a starting point, in the current state of the...

Not fully understand the normalization you have in mind. Are you referring to passing a set of constant scalars to be applied to the output of the dynamics model?

Hi @natolambert, thanks for the PR! I have a few questions: - I'm wondering if having a new replay buffer class for this is overkill, couldn't we just store the...

> This seems like a good direction, I'm realizing I will need to add another class similar to `OneDTransitionRewardModel` because the prediction formulation is as follows (rather than one step):...

That's a nice plot! I'll take a closer look at this soon (hopefully tomorrow Friday, if I have time). Thanks!

If everything you need to run this example is in the notebook, then that's definitely a good starting point! In that case I can focus on reviewing the notebook more...

Hi Nathan, that sounds good, I'm OK with this plan.

Hi @MickShen7558. We were discussing this a bit and @fantaosha agreed to add support for this pretty soon. The case where this is supported for `torch.Tensor` type inputs should be...

Hi @chenxi-yang, thanks for the report. Can you be more explicit on the errors you are getting? Is it not learning at all, or is it that the reward less...