Table of Contents
This repository/package contains Jupyter Notebooks with examples on how to use EAGERx. EAGERx (Engine Agnostic Graph Environments for Robotics) enables users to easily define new tasks, switch from one sensor to another, and switch from simulation to reality with a single line of code by being invariant to the physics engine.
The core repository is available here.
Full documentation and tutorials (including package creation and contributing) are available here.
The following tutorials are currently available.
Introduction to EAGERx
The solutions are available in here.
Developer tutorials
- Tutorial 1: Environment Creation and Training with EAGERx
- Tutorial 2: Reset and Step
- Tutorial 3: Space and Processors
- Tutorial 4: Nodes and Graph Validity
- Tutorial 5: Adding Engine Support for an Object
- Tutorial 6: Defining a new Object
- Tutorial 7: More Informative Rendering
- Tutorial 8: Reset Routines
The solutions are available in here.
As an alternative to running the tutorials in Google Colab, they can also be run locally in order to speed up computations.
Clone this repository and go to its root:
git clone git@github.com:eager-dev/eagerx_tutorials.git
cd eagerx_tutorialsOptional Create and source a virtual environment, (if venv is not installed run python3 -m pip install --user virtualenv):
python3 -m venv tutorial_env
source tutorial_env/bin/activateInstall the eagerx_tutorials package:
pip3 install -e .Start Jupyter Lab:
jupyter labYou will find the tutorials in the tutorials directory.
If you are using EAGERx for your scientific publications, please cite:
@article{vanderheijden2024eagerx,
title={EAGERx: Graph-Based Framework for Sim2real Robot Learning},
author={van der Heijden, Bas and Luijkx, Jelle and Ferranti, Laura and Kober, Jens and Babuska, Robert},
journal={arXiv preprint arXiv:2407.04328},
year={2024}
}EAGERx is funded by the OpenDR Horizon 2020 project.