-
Howdy Brax team!
Can we update progress_fn arguments take and return params, in addition to metrics, at each checkpoint during training?
Yours,
Vijay
-
## Describe the bug
Collectors seem to have been designed to work with enviornments with empty `batch_size`.
Examples of torchrl environments where colllectors do not work are Brax (with a batch…
-
The V2 version Brax is just in time for my thesis and already helping me a lot! Thanks for all the work.
However, changing the parameters of an brax environment is not yet trivial. I know v2 is still…
-
When I try to play saved html visualization on my local computer I always get this error in HTML:
Uncaught TypeError: Cannot read property '0' of undefined
at demo.html:191
at Array.map ()
…
-
### Describe the bug
# The problem
due to https://github.com/openai/gym/pull/2762#issuecomment-1135362092 it was decided that `use_contact_forces` would default to `False`, but
The 2 different prob…
-
I ran into the following error while following the conda installation instructions:
```
third_party/pybind11/include/pybind11/cast.h:446:36: error: invalid use of incomplete type ‘PyFrameObj…
-
Hi,
I created a simple motorized pendulum environment to confirm doubt I had regarding BRAX's nomenclature.
It has a fixed body, and a link + actuator linking it to a swinging body with a certain …
-
Is it expected that Ant with the generalized pipeline runs 40 times slower compared to the Spring pipeline? (Generalized sps: ~2100, spring: ~85000)
I am running the regular Brax v2 training loop w…
-
Hi,
I am currently working on a project where I want to replicate this robot in brax
…
-
Comparing HalfCheetah in Brax (via gym.make and then wrapped as here: https://github.com/google/brax/blob/main/notebooks/training_torch.ipynb) vs in CARL makes a big difference in return even when the…