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 2602.12458cs.MA
收藏

基于理论思维的策略适应零样本协调理论

Theory of Mind Guided Strategy Adaptation for Zero-Shot Coordination

Carnegie Mellon University（卡内基梅隆大学）；Virginia Tech（弗吉尼亚理工大学）；University of Southern California（南加州大学）；University of Pittsburgh（匹兹堡大学）

Andrew Ni, Simon Stepputtis, Stefanos Nikolaidis, Michael Lewis, Katia P. Sycara, Woojun Kim

备注：
Accepted at the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出基于理论思维的适应性集成智能体，通过推断队友意图并选择合适策略，提升零样本协调性能。

摘要：

多智能体强化学习中的核心挑战在于使智能体能够以零样本的方式适应之前未见过的队友。以往的零样本协调工作通常遵循两阶段过程，首先生成一个多样化的训练池伙伴智能体，然后训练一个最佳响应智能体以有效与整个训练池协作。尽管许多先前工作通过设计更好的方法来多样化伙伴智能体池实现了强劲性能，但对如何利用该池来构建适应性智能体的关注较少。一个限制是最佳响应智能体可能会收敛到一个静态、通用策略，该策略在多样化的队友上表现尚可，而不是学习一个更具适应性和专业性的策略，能够更好地适应队友并实现更高的协同效应。为了解决这个问题，我们提出了一种适应性集成智能体，它使用基于理论思维的最佳响应选择来首先推断其队友的意图，然后从策略集成中选择最合适的策略。我们在Overcooked环境中进行实验，评估在完全和部分可观测设置下的零样本协调性能。实证结果展示了我们的方法优于单一最佳响应基线。

英文摘要：

A central challenge in multi-agent reinforcement learning is enabling agents to adapt to previously unseen teammates in a zero-shot fashion. Prior work in zero-shot coordination often follows a two-stage process, first generating a diverse training pool of partner agents, and then training a best-response agent to collaborate effectively with the entire training pool. While many previous works have achieved strong performance by devising better ways to diversify the partner agent pool, there has been less emphasis on how to leverage this pool to build an adaptive agent. One limitation is that the best-response agent may converge to a static, generalist policy that performs reasonably well across diverse teammates, rather than learning a more adaptive, specialist policy that can better adapt to teammates and achieve higher synergy. To address this, we propose an adaptive ensemble agent that uses Theory-of-Mind-based best-response selection to first infer its teammate's intentions and then select the most suitable policy from a policy ensemble. We conduct experiments in the Overcooked environment to evaluate zero-shot coordination performance under both fully and partially observable settings. The empirical results demonstrate the superiority of our method over a single best-response baseline.

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。

↑