arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.14718cs.AI
收藏

优化人类与AI协作智能体之间的委派

Optimizing delegation between human and AI collaborative agents

Università di Pisa(比萨大学);Institute for Informatics and Telematics (IIT), National Research Council (CNR)(国家研究委员会(CNR)信息学与电信研究所(IIT))

Andrew Fuchs, Andrea Passarella, Marco Conti

AI总结:

针对混合团队中人类与AI智能体协作,提出学习委派决策的管理模型,无需智能体共享环境动态,显著优于其他管理方法。

摘要:

在人类与人工或自主智能体组成的混合团队中运作的背景下,准确识别何时授权这些团队成员执行动作至关重要。鉴于过去人类与自主系统在任务中可能成功或失败的例子,我们寻求训练一个委派管理智能体,针对这些潜在的性能缺陷做出委派决策。此外,我们不能总是期望各个智能体在相同的环境底层模型下运作。可能会遇到不同智能体之间动作和状态转换各异的情况。因此,我们的框架提供了一个管理模型,它通过观察团队绩效来学习,而不限制智能体必须匹配动态。我们的结果表明,我们的管理智能体能够学习在具有不同环境表示的智能体团队中做出委派决策,显著优于管理团队的其他替代方法。

英文摘要:

In the context of humans operating with artificial or autonomous agents in a hybrid team, it is essential to accurately identify when to authorize those team members to perform actions. Given past examples where humans and autonomous systems can either succeed or fail at tasks, we seek to train a delegating manager agent to make delegation decisions with respect to these potential performance deficiencies. Additionally, we cannot always expect the various agents to operate within the same underlying model of the environment. It is possible to encounter cases where the actions and transitions would vary between agents. Therefore, our framework provides a manager model which learns through observations of team performance without restricting agents to matching dynamics. Our results show our manager learns to perform delegation decisions with teams of agents operating under differing representations of the environment, significantly outperforming alternative methods to manage the team.

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。

↑