legged_gym
- Software
- Humanoids and robot learning
- Framework
A training environment built on NVIDIA Isaac Gym for teaching legged robots, such as ANYmal, to walk over rough terrain with sim-to-real transfer features.
- Closed core
- Stale
- Moved
Made by ETH Zurich Robotic Systems Lab and NVIDIA, Switzerland (checked on github.com/leggedrobotics/legged_gym/blob/master/LICENSE (opens in a new tab)).
Source on GitHub: github.com/leggedrobotics/legged_gym (opens in a new tab). Facts read at commit 8fa29ac (opens in a new tab).
Licenses
- Code
- BSD-3-Clause (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (BSD-3-Clause) at commit 8fa29ac (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Unknown
It needs closed parts under their own terms: read them before any commercial use.
One part it needs is closed
- Needs NVIDIA Isaac Gym Preview 3: Needed for training; closed, and discontinued by NVIDIA.
Labels
- Closed coreIt needs closed parts: NVIDIA Isaac Gym Preview 3.
- StaleNo commit in 12 months: the newest is from 29 May 2025.
- MovedMoved to a new home, not on Robotheca yet.
What it does
- Trains legged robot locomotion policies on rough terrain using NVIDIA Isaac Gym.
- Includes an actuator network, friction and mass randomization, noisy observations, and random pushes during training.
- Environments are defined by env and config files that use inheritance, and tasks are registered for training.
- Trained policies are saved as model checkpoints and can be replayed with a play script.
- Training can run headless or on CPU, with simulation and RL devices set separately.
- The maintainers have moved their environments to Isaac Lab, so this repository gets only limited updates.
Written by Robotheca from the project's README (opens in a new tab) at commit 8fa29ac.
Getting started
- Difficulty
- Advanced
- How to start
- The project's README (opens in a new tab)
Maintenance
- Status
- Stale: no commit in 12 months
- Newest commit
- 29 May 2025 on master
- Latest release
- None published on GitHub
- Moved
- Its new home is not on Robotheca yet.
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.