Abstract
Deep reinforcement learning has recently been applied to a variety of robotics applications, but learning locomotion for robots with unconventional configurations is still limited. Prior work has shown that, despite the simple modeling of articulated swimmer robots, such systems struggle to find effective gaits using reinforcement learning due to the heterogeneity of the search space. In this work, we leverage insight from geometric models of these robots in order to focus on promising regions of the space and guide the learning process. We demonstrate that our augmented learning technique is able to produce gaits for different learning goals for swimmer robots in both low and high Reynolds number fluids.
Abstract (translated)
深度学习最近被应用于多种机器人应用中,但对于具有非常规配置的机器人的学习行走仍然有限。先前的工作表明,尽管这些组合机器人模型非常简单,但这些系统由于搜索空间的多样性,使用强化学习难以找到有效的步态。在本文中,我们利用这些机器人的几何模型来借鉴 insights,并将注意力集中在空间中的有希望区域,指导学习过程。我们证明,我们的增强学习技术能够为低和高 Reynolds number流体中的游泳机器人制造不同的学习目标步态。
URL
https://arxiv.org/abs/2301.13072
