arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.00751cs.LGcs.AIcs.MAcs.ROstat.ML
收藏

分散合作Bandit团队中的伙伴感知算法

Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams

Stanford University(斯坦福大学);Princeton University(普林斯顿大学)

Erdem Bıyık, Anusha Lalitha, Rajarshi Saha, Andrea Goldsmith, Dorsa Sadigh

摘要:

当人类彼此合作时,他们通常通过观察他人并考虑他们的行为可能对整个团队产生的后果来做出决定,而不是只为自己做最好的事情。我们希望我们的人工智能智能体通过捕获其合作伙伴的模型来以类似的方式进行有效合作。在这项工作中,我们提出并分析了一个分散的多臂强盗(MAB)问题与耦合奖励更一般的多智能体协作的抽象。我们证明,天真的扩展单代理最优MAB算法失败时,分散的强盗队。相反,我们提出了一个合作伙伴意识的联合顺序决策策略,扩展了著名的单代理置信上限算法。我们分析表明,我们提出的策略实现了对数遗憾,并提供了涉及人类-AI和人类-机器人协作的广泛实验,以验证我们的理论研究结果。我们的研究结果表明,所提出的伙伴意识策略优于其他已知的方法,我们的人类受试者研究表明,人类更喜欢与实施我们的伙伴意识策略的人工智能智能体合作。

英文摘要:

When humans collaborate with each other, they often make decisions by observing others and considering the consequences that their actions may have on the entire team, instead of greedily doing what is best for just themselves. We would like our AI agents to effectively collaborate in a similar way by capturing a model of their partners. In this work, we propose and analyze a decentralized Multi-Armed Bandit (MAB) problem with coupled rewards as an abstraction of more general multi-agent collaboration. We demonstrate that naïve extensions of single-agent optimal MAB algorithms fail when applied for decentralized bandit teams. Instead, we propose a Partner-Aware strategy for joint sequential decision-making that extends the well-known single-agent Upper Confidence Bound algorithm. We analytically show that our proposed strategy achieves logarithmic regret, and provide extensive experiments involving human-AI and human-robot collaboration to validate our theoretical findings. Our results show that the proposed partner-aware strategy outperforms other known methods, and our human subject studies suggest humans prefer to collaborate with AI agents implementing our partner-aware strategy.

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。

↑