brax icon indicating copy to clipboard operation
brax copied to clipboard

Massively parallel rigidbody physics simulation on accelerator hardware.

Results 146 brax issues
Sort by recently updated
recently updated
newest added

Hi Brax, I'm not sure if this is an issue, but its just tripped me up, so I figured I'd put it here. In the RL demo (e.g. [here](https://github.com/google/brax/blob/main/notebooks/training.ipynb)), the...

good first issue

Hello, I am trying to run some experiments using pytorch with the JaxToTorchWrapper. I'm running the default `Training in Brax with PyTorch on GPUs` on a local jupyter instance, but...

good first issue

Hey 👋 I am working in my fork on supporting [agent specific observations](https://github.com/google/brax/blob/8a3ea6065866f687cf657d4fc5c91d002a75f72f/brax/experimental/composer/agent_utils.py#L36) in the composer sub-package. Additionally I need this feature to support observation masking that is dependent on...

I was trying to extend the domain randomization examples to include changing collider shapes using the code below. However, the renderer doesn't pick up the changes. Specifically this occurs because...

In the docstring for the `Reacher` environment, two of the elements of the observation are the angular velocities of the two arms. Inside `_get_obs` it seems to me that the...

It occurred to me that this recent paper is an interesting one to implement inside brax One of the cool things about brax is its differentiability, but as I understand...

Hello, I'm modifying a repository that depends heavily on Brax to work, but the version they use is terribly out of date so I am forced to modify things to...

Since `gym` is deprecated in favor of `gymnasium` (see https://github.com/openai/gym?tab=readme-ov-file#important-notice) here I propose the switch, allowing both installation as alternative to keep backwards compatibilty. This allows for use of python>=3.10,...

Hi, the notebook on the jax + torch tutorial is very nice and useful for me, but it uses a certain flag: `os.environ["XLA_PYTHON_CLIENT_ALLOCATOR"] = "platform"` I understand this flag prevents...

Hi all, I work on a cluster with cuda 12.4. I'm **_trying_** to use brax through torchRL wrapper. Among many issues I keep running across some weird compatibility warning. Here...