AdamStelmaszczyk/learning2run

Our NIPS 2017: Learning to Run source code

52
/ 100
Established

This project provides the core code for training virtual musculoskeletal models to run in simulated environments. It takes in a model of a human or animal with joints and muscles, applies various reinforcement learning algorithms, and outputs a trained policy that enables the model to move autonomously and efficiently. This is primarily for biomechanical researchers and robotics engineers exploring advanced locomotion and control systems.

Use this if you are a researcher in biomechanics or robotics looking to experiment with different reinforcement learning approaches to teach simulated agents complex motor skills like running.

Not ideal if you need an out-of-the-box solution for controlling real-world robots or analyzing existing human motion data without simulation.

biomechanics simulation robot locomotion reinforcement learning research motor control modeling simulated athletics
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

55

Forks

16

Language

Python

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AdamStelmaszczyk/learning2run"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.