-
Hi,
I have a config file defining a humanoid ragdoll. I have removed all of the collisions inside this config. I expected the bodies to be able to intersect each other, instead, here's a video of t…
-
### What happened + What you expected to happen
set gpu num to ray.but ray connot use gpu
`ray.get_gpu_ids()` will always return the empty list when called from the driver. This is because Ray do…
-
#### Description
Python example appears to be broken:
#### Steps/Code to Reproduce
From the "Obtaining the data" step of the python tutorial at https://openml.github.io/openml-python/develop/exam…
-
When you run the introductory Colab notebook [Brax Training with PyTorch on GPU](https://colab.research.google.com/github/google/brax/blob/main/notebooks/training_torch.ipynb), it fails to run the sec…
-
## What
- Discuss important things about MIMIC dataset that the whole team should know
- Propose formats to analyze and share important points about MIMIC
## Why
- MIMIC has a more complicated…
-
Hi,
The AutoResetWrapper (https://github.com/google/brax/blob/5ef4f654c63855dbc5f51543772feb348d48bb77/brax/envs/wrappers.py#L123) is supposedly a way to have the environment's reset function calle…
-
Would you be interested in a PR with wrappers to convert an Environment instance into Gym and VectorGym instances? This would be similar to how the Brax wrappers work (I helped write that PR), where t…
-
I want to use a single(!) ant environment for my project and checked the steps per seconds with this script:
```python
import time
import functools
import gym
from brax import envs
import jax
…
-
Hi Brax,
Is there a way to extract from an environment the cartesian coordinates of each of the joints in the model? Getting the quaternion-based state out is easy enough, but is there an in-built…
-
Hi folks, I have a question on how the ant environment behaves initially. I'm training RL policies with 2 layer mlp's using PPO and noticed that the initial rewards become quite negative before the po…