arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.04439cs.ROcs.AIcs.HC
收藏

用于实时的人-Agent协作的自适应Agent体系结构

Adaptive Agent Architecture for Real-time Human-Agent Teaming

Carnegie Mellon University(卡内基梅隆大学);University of Pittsburgh(匹兹堡大学);University of Texas at Austin(德克萨斯大学奥斯汀分校)

Tianwei Ni, Huao Li, Siddharth Agrawal, Suhas Raja, Fan Jia, Yikang Gui, Dana Hughes, Michael Lewis, Katia Sycara

摘要:

团队合作是一组相互关联的推理,行动和行为的团队成员,促进共同的目标。团队工作理论和实验已经在人-人和代理-代理团队中产生了一组团队有效性的状态和过程。然而,人类-代理团队合作的研究较少,因为它是如此的新,并且涉及人类团队中不存在的政策和意图的不对称。为了优化人类-代理团队合作中的团队绩效,代理推断人类意图并调整其策略以实现平稳协调至关重要。大多数人类代理合作的文献都是参考学习过的人类模型来构建代理的。虽然这些代理可以保证在学习模型中表现良好,但它们对人类策略进行了大量假设,例如最优性和一致性,这在许多现实场景中是不可能的。本文在双人合作游戏《团队空间堡垒》(TSF)中提出了一种新型的无人类模型环境下的自适应代理体系结构。以往的人-人团队研究表明,TSF博弈中的互补策略和人类参与者技能的多样性,这鼓励我们放松对人类策略的假设。因此,我们放弃了从人类数据中学习人类模型,而是在由RL算法或基于规则的方法组成的预先训练的范例策略库上使用自适应策略,其中对人类行为的假设最少。适应策略依赖于一种新的相似性度量来推断人类的政策,然后选择我们的库中最互补的政策,以最大限度地提高团队的绩效。自适应代理体系结构可以实时的【形】部署,并推广到任何现成的静态代理。我们进行了人类代理实验,以评估所提出的自适应代理框架,并证明了次优,多样性和人类代理团队的人类政策的适应性。

英文摘要:

Teamwork is a set of interrelated reasoning, actions and behaviors of team members that facilitate common objectives. Teamwork theory and experiments have resulted in a set of states and processes for team effectiveness in both human-human and agent-agent teams. However, human-agent teaming is less well studied because it is so new and involves asymmetry in policy and intent not present in human teams. To optimize team performance in human-agent teaming, it is critical that agents infer human intent and adapt their polices for smooth coordination. Most literature in human-agent teaming builds agents referencing a learned human model. Though these agents are guaranteed to perform well with the learned model, they lay heavy assumptions on human policy such as optimality and consistency, which is unlikely in many real-world scenarios. In this paper, we propose a novel adaptive agent architecture in human-model-free setting on a two-player cooperative game, namely Team Space Fortress (TSF). Previous human-human team research have shown complementary policies in TSF game and diversity in human players' skill, which encourages us to relax the assumptions on human policy. Therefore, we discard learning human models from human data, and instead use an adaptation strategy on a pre-trained library of exemplar policies composed of RL algorithms or rule-based methods with minimal assumptions of human behavior. The adaptation strategy relies on a novel similarity metric to infer human policy and then selects the most complementary policy in our library to maximize the team performance. The adaptive agent architecture can be deployed in real-time and generalize to any off-the-shelf static agents. We conducted human-agent experiments to evaluate the proposed adaptive agent framework, and demonstrated the suboptimality, diversity, and adaptability of human policies in human-agent teams.

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。

↑