arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.16015cs.RO
收藏

MQE:通过多智能体四足机器人环境释放交互的潜力

MQE: Unleashing the Power of Interaction with Multi-agent Quadruped Environment

Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院);AI Institute, Beijing University of Posts and Telecommunications(北京邮电大学人工智能研究院);Zhipu AI(智谱AI);Paradigm Inc.(第四范式公司);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Shanghai Qi Zhi Institute(上海期智研究院)

Ziyan Xiong, Bo Chen, Shiyu Huang, Wei-Wei Tu, Zhaofeng He, Yang Gao

AI总结:

本文提出多智能体四足机器人环境MQE,用于在真实动态场景中开发和评估多智能体强化学习算法,通过设计协作与竞争任务并基准测试现有算法,发现层次化强化学习能简化任务学习,为多智能体系统研究提供支持。

摘要:

深度强化学习(DRL)的出现显著推进了机器人学领域,特别是在四足机器人的控制和协调方面。然而,现实世界任务的复杂性往往需要部署能够进行复杂交互和协作的多机器人系统。为了满足这一需求,我们引入了多智能体四足机器人环境(Multi-agent Quadruped Environment, MQE),这是一个旨在促进在真实和动态场景中开发和评估多智能体强化学习(MARL)算法的新颖平台。MQE强调机器人与物体之间的复杂交互、层次化策略结构,以及反映现实世界应用的具有挑战性的评估场景。我们在MQE中提出了一系列协作和竞争任务,从简单的协调到复杂的对抗交互,并对最先进的MARL算法进行了基准测试。我们的研究结果表明,层次化强化学习可以简化任务学习,但也强调需要能够处理多智能体交互复杂动态的先进算法。MQE作为弥合仿真与实际部署之间差距的基石,为多智能体系统和机器人学习的未来研究提供了丰富的环境。有关MQE的开源代码和更多细节,请访问 https://ziyanx02.github.io/multiagent-quadruped-environment/ 。

英文摘要:

The advent of deep reinforcement learning (DRL) has significantly advanced the field of robotics, particularly in the control and coordination of quadruped robots. However, the complexity of real-world tasks often necessitates the deployment of multi-robot systems capable of sophisticated interaction and collaboration. To address this need, we introduce the Multi-agent Quadruped Environment (MQE), a novel platform designed to facilitate the development and evaluation of multi-agent reinforcement learning (MARL) algorithms in realistic and dynamic scenarios. MQE emphasizes complex interactions between robots and objects, hierarchical policy structures, and challenging evaluation scenarios that reflect real-world applications. We present a series of collaborative and competitive tasks within MQE, ranging from simple coordination to complex adversarial interactions, and benchmark state-of-the-art MARL algorithms. Our findings indicate that hierarchical reinforcement learning can simplify task learning, but also highlight the need for advanced algorithms capable of handling the intricate dynamics of multi-agent interactions. MQE serves as a stepping stone towards bridging the gap between simulation and practical deployment, offering a rich environment for future research in multi-agent systems and robot learning. For open-sourced code and more details of MQE, please refer to https://ziyanx02.github.io/multiagent-quadruped-environment/ .

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。

↑