myosuite

MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API

What is myosuite?

MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API.

Overview of myosuite

What it is

MyoSuite is a collection of musculoskeletal environments and tasks simulated with the MuJoCo physics engine and wrapped in the OpenAI Gym API (now Gymnasium). It is designed for researchers and practitioners in biomechanics, neuroscience, machine learning, sports medicine, and physical rehabilitation.

Key features

  • Supports multiple backends: CPU via the standard Gymnasium interface, GPU via mjlab for massively parallel training, and an experimental MJX (JAX) path.
  • Muscle conditions such as motor noise, fatigue, sarcopenia, and reafferentation are implemented as wrappers, applied identically across CPU and GPU environments.
  • Includes the complete MyoChallenge suite as Gymnasium environments: Baoding, Bimanual, Chase Tag, Die Reorient, OSL Run, Relocate, Soccer, and Table Tennis.
  • Provides MuscleMimic support for full-body and bimanual policies with ready-to-use checkpoints and motion datasets.
  • Uses a compact task specification system that allows describing new tasks in a few lines without writing a full environment class.
  • Ships with default trained policies on Hugging Face and updated tutorials.

Use cases

  • Training reinforcement learning agents on musculoskeletal control tasks.
  • Simulating and studying motor control in biomechanics and neuroscience research.
  • Developing and testing rehabilitation or sports medicine interventions.
  • Evaluating muscle condition effects (fatigue, sarcopenia, etc.) on movement.

Getting started

Install from source (recommended): bash git clone https://github.com/MyoHub/myosuite.git cd myosuite pip install -e .[rl] # CPU training (Stable-Baselines3) Or from PyPI: pip install -U myosuite. Verify installation: bash python -c 'import myosuite; print(len(myosuite.myosuite_env_suite), envs)' Quick start example: python from myosuite import make_env env = make_env(myoElbowPose1D6MRandom-v0) obs, info = env.reset(seed=0) for _ in range(1000): obs, reward, terminated, truncated, info = env.step(env.action_space.sample()) if terminated or truncated: obs, info = env.reset() env.close()

License and pricing

Licensed under Apache-2.0. The project is open source and free to use.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/myohubmyosuite.svg)](https://yunodb.com/tools/myohubmyosuite?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/myohubmyosuite?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/myohubmyosuite.svg" alt="Featured on YunoDB" height="20"></a>