dexterity 0.0.7

Software and tasks for dexterous multi-fingered hand manipulation, powered by MuJoCo

The MuJoCo Dexterity Suite (alpha-release)

Software and tasks for dexterous multi-fingered hand manipulation, powered by MuJoCo.

dexterity builds on dm_control and provides a collection of modular components that can be used to define rich Reinforcement Learning environments for dexterous manipulation. It also comes with a set of standardized tasks that can serve as a performance benchmark for the research community.

An introductory tutorial is available as a Colab notebook:

Installation

PyPI (Recommended)

The recommended way to install this package is via PyPI:

pip install dexterity

Source

We provide a Miniconda environment with Python 3.8 for development. To create it and install dependencies, run the following steps:

git clone https://github.com/kevinzakka/dexterity
cd dexterity
conda env create -f environment.yml  # Creates a dexterity env.
conda activate dexterity
pip install .

Overview

The MuJoCo dexterity suite is composed of the following core components:

• models: MuJoCo models for dexterous hands and PyMJCF classes for dynamically customizing them.
• inverse_kinematics: Inverse kinematics solver for multi-fingered hands.
• effectors: Interfaces for controlling hands and defining action spaces.

These components in conjunction with dm_control allow you to define and customize rich environments for reinforcement learning.

dexterity also comes pre-packaged with a suite of benchmark RL environments. Our hope is to grow it over time with crowd-sourced contributions from the research community. For an overview of the current tasks, see the task library.

Acknowledgements

A large part of the design and implementation of dexterity is inspired by the MoMa library in dm_robotics.