# unitreerobotics/unitree_rl_lab

This is a repository for reinforcement learning implementation for Unitree robots, based on IsaacLab.

Repository: https://github.com/unitreerobotics/unitree_rl_lab
Canonical: https://ross.abutalabs.com/products/unitree_rl_lab
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-05-25T07:08:45+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 84, release rhythm 35, longevity 32
- inputs: {"age_days": 454, "days_push": 100, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1306, forks 312 (observed 2026-08-28T04:04:18.806866+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: reinforcement-learning, simulation, machine-learning, robotics
- domain: robotics, reinforcement-learning, simulation, machine-learning
- platform: python
- tags: unitree, isaaclab, isaac-sim, legged-robots, sim-to-real, locomotion, humanoid, quadruped, mujoco, linux, gpu

## Member repositories
- unitreerobotics/unitree_rl_lab (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:18.806866+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:50:59.234044+00:00, confidence not recorded.
  - readme: https://github.com/unitreerobotics/unitree_rl_lab (fetched 2026-08-28T04:04:18.806866+00:00, sha e2dea9898482)
- Data as of 2026-08-30T08:39:29.467469+00:00.