unitreerobotics/unitree_rl_lab

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1306 stars · 312 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A collection of reinforcement learning environments for Unitree robots (Go2, H1, G1) built on NVIDIA IsaacLab. It enables training locomotion policies in simulation and deploying them to physical robots via sim-to-real transfer.

Use cases

• train RL locomotion policies for Unitree Go2 quadruped
• train humanoid walking policies for Unitree G1 and H1
• sim-to-real transfer of learned robot controllers
• set up IsaacLab environments for Unitree robots
• evaluate trained policies in MuJoCo before deployment
• research legged robot reinforcement learning

When to choose

• you own or target Unitree robots and want RL-based locomotion
• you already use IsaacLab/Isaac Sim and need Unitree environments
• you want a maintained sim-to-real pipeline for legged robots

When to avoid

• you need RL environments for non-Unitree robots
• you cannot run NVIDIA Isaac Sim on a GPU machine
• you want a general-purpose RL library rather than robot-specific environments

Facets

library · maturity active

reinforcement-learning simulation machine-learning robotics robotics reinforcement-learning simulation machine-learning python unitree isaaclab isaac-sim legged-robots sim-to-real locomotion humanoid quadruped mujoco linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="unitreerobotics/unitree_rl_lab")