An example using an LLM to navigate a quadruped in an unknown environment through trial and error. Based on mujoco playground.
-
Updated
Apr 16, 2025 - Python
#
mujoco-playground
Here are 9 public repositories matching this topic...
Reinforcement learning policies trained in NVIDIA Isaac Lab & MuJoCo Warp for robots: asimov-1 (humanoid, PPO+AMP omni-gait), v1x1 (quadruped, PPO omni-gait), BDX-R (biped, omni-gait) and Microduck (biped, omni-gait & fall recovery) with live ROS2 teleop bridges for real-time keyboard control and other sim-to-real pipelines..
reinforcement-learning simulation reinforcement-learning-algorithms ros2 mujoco reinforcement-learning-agent mujoco-py mujoco-environments reinforcement-learning-environments isaac-sim sim-to-real ros2-control isaac-ros ros2-humble mujoco-python ros2-jazzy isaac-lab mujoco-playground mujoco-warp
-
Updated
Nov 3, 2026 - Python
Repository created using https://github.com/google-deepmind/mujoco_playground as base in order to add the Go2 walking and handstand policies. It contains the code to train and simulate the policy.
-
Updated
Jan 30, 2026 - Jupyter Notebook
A small humanoid robot you can talk to: walks with a reinforcement-learned policy, waves and dances, shows a face with lip sync and speaks - its brain is a local LLM you run yourself (Ollama or any OpenAI-compatible API). MuJoCo simulation, sim-to-real.
python text-to-speech reinforcement-learning robotics locomotion humanoid-robot humanoid legged-robots mujoco jax companion-robot sim-to-real brax social-robot llm local-llm ollama mujoco-playground robot-face robotis-op3
-
Updated
Nov 1, 2026 - Python
Run JAX and MuJoCo MJX on AMD Ryzen AI MAX (Strix Halo, gfx1151) from pip wheels - no system ROCm - with a hang-safe check that tells you which wheel set works
python reinforcement-learning robotics amd gpu rocm apu mujoco uv jax amd-gpu xla mjx mujoco-playground compatibility-matrix strix-halo gfx1151 ryzen-ai-max radeon-8060s yserver
-
Updated
Nov 1, 2026 - Python
Self-paced learning and playground for robotics control software architecture and design patterns
-
Updated
Feb 13, 2025 - Python
Sparse, Residual World Models for Object-Centric Manipulation — code, paper, and browser demo
reinforcement-learning robotics pytorch mujoco mujoco-py world-models mujoco-environments reinforcement-learning-environments mujoco-python mujoco-mjx mujoco-playground
-
Updated
Oct 14, 2026 - Python
🦿 Agility Cassie learns to walk & run — trained with MuJoCo Playground (MJX + Brax PPO) on a GPU, driven from your keyboard on a CPU with plain MuJoCo + NumPy.
reinforcement-learning robotics legged-robots cassie mujoco ppo jax sim-to-real brax mjx mujoco-playground bipedal-locomotion
-
Updated
Oct 6, 2026 - Jupyter Notebook
Sim2real transfer of a RL policy using brax and mujoco
-
Updated
Nov 24, 2025 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the mujoco-playground topic, visit your repo's landing page and select "manage topics."