ReleaseGoogle (DeepMind / Gemini)Google (DeepMind / Gemini)published Mar 7, 2025seen 5d

google-deepmind/mujoco_playground v0.0.4

google-deepmind/mujoco_playground

Open original ↗

Captured source

source ↗
published Mar 7, 2025seen 5dcaptured 9hhttp 200method plain

Release v0.0.4

Repository: google-deepmind/mujoco_playground

Tag: v0.0.4

Published: 2025-03-07T19:25:32Z

Prerelease: no

Release notes:

Added

  • Added ALOHA handover task (thanks to @Andrew-Luo1).
  • Added Booster T1 joystick task.

https://github.com/user-attachments/assets/3cf2a015-f405-4899-948e-6dc4f19eb91b

https://github.com/user-attachments/assets/c138a386-eb42-4bb4-a8f0-7393406e9557

Changed

  • Fixed foot friction randomization for G1 tasks.
  • Fix various bugs in train_jax_ppo.py (thanks to @vincentzhang).
  • Fixed a small bug in the privileged state of the go1 joystick task.

Notability

notability 3.0/10

Routine patch release of a tool library