arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.02395cs.RO
收藏

模块化机器人的深度强化学习方法评价

Evaluation of Deep Reinforcement Learning Methods for Modular Robots

Erle Robotics(厄勒机器人公司)

Risto Kojcev, Nora Etxezarreta, Alejandro Hernández, Víctor Mayoral

摘要:

我们提出了一个新的框架,深度强化学习(DRL)在模块化机器人使用传统的机器人工具,扩展国家的最先进的DRL实现,并提供一个端到端的方法,直接从关节状态训练机器人。此外,我们提出了一种新的技术,将这些DLR方法转移到真正的机器人,旨在关闭模拟现实的差距。我们展示了最先进的DRL方法在模块化机器人中连续动作空间的性能的鲁棒性,在模拟和真实机器人中进行了实证研究,我们还评估了加速模拟时间如何影响机器人的性能。我们的研究结果表明,扩展模块化机器人从3度的自由度(DoF),4自由度,不影响机器人的学习。这为使用DRL技术训练模块化机器人铺平了道路。

英文摘要:

We propose a novel framework for Deep Reinforcement Learning (DRL) in modular robotics using traditional robotic tools that extend state-of-the-art DRL implementations and provide an end-to-end approach which trains a robot directly from joint states. Moreover, we present a novel technique to transfer these DLR methods into the real robot, aiming to close the simulation-reality gap. We demonstrate the robustness of the performance of state-of-the-art DRL methods for continuous action spaces in modular robots, with an empirical study both in simulation and in the real robot where we also evaluate how accelerating the simulation time affects the robot's performance. Our results show that extending the modular robot from 3 degrees-of-freedom (DoF), to 4 DoF, does not affect the robot's learning. This paves the way towards training modular robots using DRL techniques.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑