Is mujoco a good choice as a robotics/ML workbench?

[WascallyWabbit]

Intro

Hi!

I am a renegade computer nerd at home. I don't use MuJoCo yet, but I'm thinking about it.

I have some experience working on path finding algorithms for cars at a company that specialized in LiDAR. I want to make an emulation where simple car-like bots find their way around a block world without striking any blocks, guided by simulated-LiDARish sensors. I want the movements of the cars to be learned, and intend to put most of my energy into tinkering with learning algorithms, etc.; the graphics and the UI can be really crude.

Eric
PS. I have coding skills.

My setup

C, maybe Python, x86_64, Ubuntu 24.04

My question

Is mujoco designed with this use case in mind? I see the BRAX bit. Is this the tool for me? Is it actively and widely used?

Minimal model and/or code that explain my question

If you encountered the issue in a complex model, please simplify it as much as possible (while still reproducing the issue).

Model:

minimal XML

<mujoco>
  <worldbody>
    <light pos="0 0 1"/>
    <geom type="sphere" size="1" rgba="1 0 0 1"/>
  </worldbody>
</mujoco>

Code:

import mujoco
import mediapy as media
model = mujoco.MjModel.from_xml_string(xml)
data = mujoco.MjData(model)

with mujoco.Renderer(model) as renderer:
  mujoco.mj_forward(model, data)
  renderer.update_scene(data)

  media.show_image(renderer.render())

Confirmations

• I searched the latest documentation thoroughly before posting.
• I searched previous Issues and Discussions, I am certain this has not been raised before.

[WascallyWabbit]

I have found what I need - except the 'delete posting' option. This is SPAM.