@btaba.bsky.social
Robotics at Google Deepmind. I work on MJX, MuJoCo, and brax.
Feel free to check out the technical report playground.mujoco.org/assets/playg...
But most importantly, we welcome more contributors to try out Playground and to join the open-source sim ecosystem to push the frontier of robotics.
But most importantly, we welcome more contributors to try out Playground and to join the open-source sim ecosystem to push the frontier of robotics.
playground.mujoco.org
January 16, 2025 at 11:12 PM
Feel free to check out the technical report playground.mujoco.org/assets/playg...
But most importantly, we welcome more contributors to try out Playground and to join the open-source sim ecosystem to push the frontier of robotics.
But most importantly, we welcome more contributors to try out Playground and to join the open-source sim ecosystem to push the frontier of robotics.
I also want to highlight hard work from collaborators to hook up MJX with the Madrona batch renderer (via github.com/shacklettbp/...).
I'm super impressed that Mustafa Haiderbhai and Jing Yuan Luo were able to train a pick-cube policy in 10 minutes from pixels on a 1x RTX 4090
I'm super impressed that Mustafa Haiderbhai and Jing Yuan Luo were able to train a pick-cube policy in 10 minutes from pixels on a 1x RTX 4090
January 16, 2025 at 11:10 PM
I also want to highlight hard work from collaborators to hook up MJX with the Madrona batch renderer (via github.com/shacklettbp/...).
I'm super impressed that Mustafa Haiderbhai and Jing Yuan Luo were able to train a pick-cube policy in 10 minutes from pixels on a 1x RTX 4090
I'm super impressed that Mustafa Haiderbhai and Jing Yuan Luo were able to train a pick-cube policy in 10 minutes from pixels on a 1x RTX 4090
As well as a non-prehensile high frequency torque control policy:
January 16, 2025 at 11:07 PM
As well as a non-prehensile high frequency torque control policy:
I'm particularly excited about the manipulation results, which used our MuJoCo MJX simulator to train dexterous manipulation policies:
January 16, 2025 at 11:06 PM
I'm particularly excited about the manipulation results, which used our MuJoCo MJX simulator to train dexterous manipulation policies: