-
The training wrappers for auto reset and episode wrapper are leaking info to each other.
This is a bigger problem if people want to stack their own wrappers. For example, I'd like to write a meta-e…
-
When I run the **Imports and installations section** of [differentiable physics tutorial](https://colab.research.google.com/github/google-deepmind/mujoco/blob/main/mjx/training_apg.ipynb#scrollTo=BGoe…
-
For robots like fixed-base serial manipulators, it is not uncommon to have `n` joints and `n+1` links, as there will be a nontrivial base link with inertial properties. For example, consider the Frank…
-
## What
Change the default learning rate setting of combination AUCM x PESG as 0.01.
In detail, the learning rate of PESG
## Why
* Fundamentally, it is important because of the high performanc…
-
## Describe the bug
With Brax, using default batch size or batch size one breaks.
1. Using default batch size gives on error
2. Using batch size = [1] gives another error
This issue might be…
-
Hi!
I am trying to extend the [Ant](https://github.com/google/brax/blob/main/brax/envs/ant.py) basic brax locomotion environment by simply adding a Trap in front of the Ant.
To do so, I took th…
-
The `brax` model loading function doesn't correctly parse some MJCF files. I'm testing the Franka Panda model from the [mujoco_menagerie repo](https://github.com/deepmind/mujoco_menagerie/tree/main/fr…
-
## Describe the bug
I ran into 2 problems (that might be related) and a third one more that I would like to point your attention to
1. brax.py seems to be using an older/different API that call…
-
Hello,
I am currently working on an RL project that involves training models from mujoco_menagerie to perform certain tasks.
I already have my own working code for the whole process, which uses …
-
Thank you for open-sourcing the work!
I am trying to visualize the diffusion process by running the commands: `python visualize_mbd.py --env_name $ENV_NAME`
However, I got the error of `Attribu…