-
Hi,
I've been trying to experiment with Pusher env using Spring as a pipeline, and had significant trouble getting anything to train. I investigated a bit and found that there seems to be something…
-
Hello,
I have been encountering an issue where my training runs error free and learns well, but then control values of NaN are generated at inference when collecting a trajectory to make a video of…
-
### Question
In the old gym lib, the documentation for the action space of Ant-v4 is differently reported: https://www.gymlibrary.dev/environments/mujoco/ant/
Theirs also matches the brax ordering…
-
Hello,
I am working on migrating some code for a library I'm writing to MJX from Brax, and am running into issues while taking gradients. I see that this has been raised in #1349 and have found ano…
-
Networks used as control policies in BRAX seem to have a `tanh` layer on the output to constrain actions to `[-1,1]`. However, many of the environments in BRAX have action spaces with a range greater …
-
Could you share the description of the programming environment? It is important for us to reproduce the results.
-
### Question
I am working with parallel environments in Isaac Sim and encountered an issue where the state of one environment affects the others during execution. Specifically, when one environment…
-
Hi MuJoCo Team,
I am a research engineer focusing on robotics, and I've been leveraging MJX, the GPU-accelerated version of MuJoCo, for simulating quadrupedal robots. First off, I want to express m…
-
Hi,
I'm a student and I'm trying to use MuJoCo for my research.
I'm looking for some help with running the tutorial on my PC.
Here is a model which explains my question:
When I wanted …
-
Hi friends,
It appears that MuJoCo officially removed `mjx.ncon` (https://mujoco.readthedocs.io/en/latest/changelog.html#version-3-1-5-may-7-2024) and hence this line is broken:
https://github.c…