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 2407.19128cs.ROcs.MA
收藏

关系 Q-函数:连续动作域中多智能体学习如何从不可预见的机器人故障中恢复

Relational Q-Functionals: Multi-Agent Learning to Recover from Unforeseen Robot Malfunctions in Continuous Action Domains

University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校)

Yasin Findik, Paul Robinette, Kshitij Jerath, Reza Azadeh

AI总结:

提出 Relational Q-Functionals (RQF) 框架,利用关系网络增强多智能体在连续动作域中对不可预见机器人故障的适应与恢复能力。

摘要:

协作多智能体学习方法对于在多智能体领域中开发有效的协作策略至关重要。在机器人技术中,这些方法不仅适用于多机器人场景,还扩展到了单机器人系统,在其中实现不同机器人模块(例如机器人腿或关节)之间的协调。然而,当前方法通常难以快速适应不可预见的故障,例如机器人腿发生故障,尤其是在算法已经收敛到某一策略之后。为了克服这一问题,我们引入了 Relational Q-Functionals (RQF) 框架。RQF 利用一个表示智能体关系的关系网络来增强适应性,从而提供针对故障的弹性。我们的算法还能高效处理连续状态-动作域,使其非常适合机器人学习任务。我们的实证结果表明,RQF 使智能体能够有效利用这些关系来促进协作,并在具有多个交互模块的单机器人系统中从意外故障中恢复。因此,我们的方法在多智能体系统中展现出广阔的应用前景,特别是在存在不可预见故障的场景中。

英文摘要:

Cooperative multi-agent learning methods are essential in developing effective cooperation strategies in multi-agent domains. In robotics, these methods extend beyond multi-robot scenarios to single-robot systems, where they enable coordination among different robot modules (e.g., robot legs or joints). However, current methods often struggle to quickly adapt to unforeseen failures, such as a malfunctioning robot leg, especially after the algorithm has converged to a strategy. To overcome this, we introduce the Relational Q-Functionals (RQF) framework. RQF leverages a relational network, representing agents' relationships, to enhance adaptability, providing resilience against malfunction(s). Our algorithm also efficiently handles continuous state-action domains, making it adept for robotic learning tasks. Our empirical results show that RQF enables agents to use these relationships effectively to facilitate cooperation and recover from an unexpected malfunction in single-robot systems with multiple interacting modules. Thus, our approach offers promising applications in multi-agent systems, particularly in scenarios with unforeseen malfunctions.

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。

↑