ROBEL (RObotics BEnchmarks for Learning): a collection of affordable, reliable hardware designs for studying dexterous manipulation and locomotion on real-world hardware. With simple assembly instructions, detailed simulations, and all open-sourced software, we hope to open up the field of Reinforcement Learning to everyone and accelerate progress around the world.

Features

1. Gym Compliant -- ROBEL environments are fully Gym-compliant and can be used with any reinforcement learning library that interfaces with Gym environments.
2. Simulated backends -- ROBEL also includes simulated equivalents of the introduced benchmarks to facilitate prototyping and debugging needs. Simulation backend is provided by MuJoCo. Support for Bullet is planned.
3. Hardware interface -- Communication with hardware is done through the DynamixelSDK.
4. External tracking support -- For D'Kitty environments, external tracking is supported through OpenVR tracking.
5. Open-source design -- The hardware design and build instructions are fully open-sourced and are available for anyone to build their own robots.