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.

翻译：目前可供研究的机器人平台要么非常昂贵,要么无法处理在强化学习中滥用探索性控制的问题。我们开发了RealAnt,这是用于强化学习的常用“Ant”基准的最低低成本物理版本。RealAnt的材料成本仅为350欧元(410美元),在不到一个小时内可以组装。我们用强化学习实验来验证该平台,并根据一套基准任务提供基线结果。我们证明ReAnt机器人能够从不到10分钟的经验中学会从零开始走路。我们还在MuJoco和PyBullet模拟器中提供机器人的模拟版本(具有相同的尺寸、状态行动空间和延迟的噪音观测)。我们为教育用途和再生研究提供开源硬件设计、支持软件和基线结果。