Hacker News new | past | comments | ask | show | jobs | submit login
MuJoco Playground (mujoco.org)
78 points by kzakka 13 days ago | hide | past | favorite | 6 comments





Playing with MuJoCo is a lot of fun. I recommend it for people who just want to experiment with RL. You can do random weird stuff like this: https://www.youtube.com/watch?v=e-9u_vepfY8. I'm really glad DeepMind is continuing to update it.

Holy Molly. The live demo where you put a place holder and the trained robot dog just goes there is insane! You can also apply force (aka kick) the robot while it is moving!

An open-source library for GPU-accelerated robot learning and sim-to-real transfer.

Really cool. If we could do sim training to rl conversion in robotics, we migth get a llm moment for robotics, with good pretrained movement algorithms.

This is great - I haven't looked at the documentation yet but do you support soft body simulation?

MuJoCo does support soft bodies:

https://mujoco.readthedocs.io/en/latest/modeling.html#deform...

The GPU part of MuJoCo only supports soft collisions rather than fully deformable bodies.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: