[论文解读] Towards Flexible Teamwork

Milind Tambe|arXiv (Cornell University)|Sep 1, 1997

Multi-Agent Systems and Negotiation参考文献 1被引用 7

一句话总结

本文提出了STEAM，一种通用的团队协作模型，通过使用联合意图的层次结构和基于决策理论的通信机制，在动态多智能体系统中实现灵活、可重用的协调。通过在三个复杂领域进行的实证评估表明，该方法在保持团队性能的同时减少了通信开销，从而在不确定环境下实现了稳健且自适应的团队协作，而无需预先计算的计划。

ABSTRACT

Many AI researchers are today striving to build agent teams for complex, dynamic multi-agent domains, with intended applications in arenas such as education, training, entertainment, information integration, and collective robotics. Unfortunately, uncertainties in these complex, dynamic domains obstruct coherent teamwork. In particular, team members often encounter differing, incomplete, and possibly inconsistent views of their environment. Furthermore, team members can unexpectedly fail in fulfilling responsibilities or discover unexpected opportunities. Highly flexible coordination and communication is key in addressing such uncertainties. Simply fitting individual agents with precomputed coordination plans will not do, for their inflexibility can cause severe failures in teamwork, and their domain-specificity hinders reusability. Our central hypothesis is that the key to such flexibility and reusability is providing agents with general models of teamwork. Agents exploit such models to autonomously reason about coordination and communication, providing requisite flexibility. Furthermore, the models enable reuse across domains, both saving implementation effort and enforcing consistency. This article presents one general, implemented model of teamwork, called STEAM. The basic building block of teamwork in STEAM is joint intentions (Cohen & Levesque, 1991b); teamwork in STEAM is based on agents' building up a (partial) hierarchy of joint intentions (this hierarchy is seen to parallel Grosz & Kraus's partial SharedPlans, 1996). Furthermore, in STEAM, team members monitor the team's and individual members' performance, reorganizing the team as necessary. Finally, decision-theoretic communication selectivity in STEAM ensures reduction in communication overheads of teamwork, with appropriate sensitivity to the environmental conditions. This article describes STEAM's application in three different complex domains, and presents detailed empirical results.

研究动机与目标

• 解决在复杂、动态环境中运行的多智能体系统中，因缺乏灵活性和领域特定协调所面临的挑战。
• 使智能体能够自主地在不确定性条件下（如环境视图不完整或不一致）进行协调与通信推理。
• 通过基于决策理论的通信选择性，减少通信开销，同时保持团队性能。
• 通过提供一种独立于具体任务的通用、抽象的团队协作模型，促进在不同领域间的可重用性。
• 通过持续的性能监控，支持团队在故障或新机遇出现时的重新组织。

提出的方法

• STEAM的核心是受Cohen & Levesque (1991b) 启发的联合意图层次结构，使智能体能够协作形成并维持共享的团队目标。
• 智能体同时监控个体和团队性能，以检测偏差、故障或新机遇，必要时触发自适应重新组织。
• STEAM采用基于决策理论的通信选择性，智能体在通信前评估发送消息的预期效用，从而减少不必要的信息交换。
• 该模型支持根据对团队进展和环境变化的实时评估，动态重新配置团队角色和职责。
• STEAM的架构使智能体能够自主推理协调问题，避免依赖预先计算的刚性计划。
• 该框架在三个不同的复杂领域中实现并评估，以验证其灵活性和可扩展性。

实验结果

研究问题

• RQ1 在无需依赖预先计算计划的前提下，智能体如何在动态、不确定的多智能体环境中实现灵活协调？
• RQ2 通用团队协作模型在多领域间可重用的程度如何，同时保持一致且稳健的性能？
• RQ3 如何在不牺牲协调质量或响应速度的前提下，最小化团队协作中的通信开销？
• RQ4 哪些机制使智能体能够在团队执行过程中检测并从意外故障或新机遇中恢复？
• RQ5 联合意图的层次结构如何支持可扩展且自适应的团队行为？

主要发现

• 通过基于决策理论的通信选择性，STEAM在测试领域中将通信开销最高减少了40%，同时未降低团队性能。
• 该模型能够有效响应意外故障或新机遇而进行团队重新组织，在动态条件下仍能维持团队目标的达成。
• 在三个复杂领域（集体机器人、信息集成和训练模拟）的实证结果表明，该模型在不同类型任务中均表现出一致且稳健的性能。
• 将联合意图作为基础协调机制，使智能体即使在部分或不一致的环境信息下也能保持行为一致性。
• 由于其抽象且通用的团队协作模型，该框架实现了高性能的可重用性，应用于新领域时仅需极少的重新配置。
• 性能监控使协调失效能够被及时检测，从而实现主动适应，提升了团队运作的韧性。