BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO
Sebastian Dittert, Vincent Moens, Gianni De Fabritiis

TL;DR
BricksRL is a platform that combines LEGO robotics with reinforcement learning, enabling accessible, real-time training and customization for research and education, with experiments demonstrating effective, low-cost robot training.
Contribution
The paper introduces BricksRL, a novel platform integrating LEGO robotics with TorchRL for real-time reinforcement learning, enhancing accessibility and customization in robotics education and research.
Findings
Inexpensive LEGO robots can be trained end-to-end in under 120 minutes.
The platform supports real-time communication and training on standard laptops.
Users can extend capabilities with additional sensors and customizations.
Abstract
We present BricksRL, a platform designed to democratize access to robotics for reinforcement learning research and education. BricksRL facilitates the creation, design, and training of custom LEGO robots in the real world by interfacing them with the TorchRL library for reinforcement learning agents. The integration of TorchRL with the LEGO hubs, via Bluetooth bidirectional communication, enables state-of-the-art reinforcement learning training on GPUs for a wide variety of LEGO builds. This offers a flexible and cost-efficient approach for scaling and also provides a robust infrastructure for robot-environment-algorithm communication. We present various experiments across tasks and robot configurations, providing built plans and training results. Furthermore, we demonstrate that inexpensive LEGO robots can be trained end-to-end in the real world to achieve simple tasks, with training…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsReinforcement Learning in Robotics
MethodsLib
