RealAnt: An Open-Source Low-Cost Quadruped for Education and Research in Real-World Reinforcement Learning
This provides an affordable and accessible platform for education and research in real-world reinforcement learning, addressing a bottleneck for students and researchers with limited budgets.
The authors tackled the problem of expensive and fragile robot platforms for reinforcement learning research by developing RealAnt, a low-cost quadruped robot that costs about 350 EUR and can be assembled in under an hour. They demonstrated that RealAnt can learn to walk from scratch in less than 10 minutes of experience and provided open-source designs and software for educational and research use.
Current robot platforms available for research are either very expensive or unable to handle the abuse of exploratory controls in reinforcement learning. We develop RealAnt, a minimal low-cost physical version of the popular `Ant' benchmark used in reinforcement learning. RealAnt costs only $\sim$350 EUR (\$410) in materials and can be assembled in less than an hour. We validate the platform with reinforcement learning experiments and provide baseline results on a set of benchmark tasks. We demonstrate that the RealAnt robot can learn to walk from scratch from less than 10 minutes of experience. We also provide simulator versions of the robot (with the same dimensions, state-action spaces, and delayed noisy observations) in the MuJoCo and PyBullet simulators. We open-source hardware designs, supporting software, and baseline results for educational use and reproducible research.