arXiv cs.MA· Ryan Park, Li-huan Shen, Jesse Milzman, Negar Mehr, David Fridovich-Keil·· 11 小时前AI 评分22
非合作动态博弈中信念失配的鲁棒方法
A Robust Approach to Belief Mismatch in Non-cooperative Dynamic Games
AI 导读
针对非合作动态博弈中智能体因私有传感器测量导致状态估计不一致的问题，研究者提出在增广信念空间中以扰动贝叶斯动力学建模，由假想对手“nature”选择扰动来刻画其他智能体信念的偏离，思路可视为经典 H-infinity 鲁棒控制向非合作随机动态博弈的扩展。配套求解器具有多项式时间迭代复杂度，两项实验显示该方法使自我智能体主动限制未来对其他智能体信念与动作模型误设的脆弱性，性能退化降低超过 48%。
正文 · 原文
Abstract:Game-theoretic models are increasingly used to describe multi-agent interactions in control and robotics applications. However, theoretical and computational complexity makes these models intractable in many dynamic, incomplete information scenarios. Recent work makes strong assumptions to reduce computational complexity: agents share sensor measurements with one another and maintain a common estimate of state uncertainty. Unfortunately, these assumptions enforce a degree of cooperation in generically noncooperative interactions. This paper takes the perspective of an ego agent seeking both computational tractability and robustness to unanticipated behavior of other agents due to mismatched state estimates from private---rather than shared---sensor measurements. To that end, we formulate the game theoretic planning problem in an augmented belief space with perturbed Bayesian dynamics that allows the ego to predict all agents' potentially divergent state estimates. These perturbations are chosen by a hypothetical adversary, ``nature,'' to reflect how non-ego agents' state estimates---based on measurements the ego agent will not see at runtime---may deviate from the ego's own belief. Ultimately, our approach can be understood in the spirit of classical H-infinity robust control, extended to noncooperative, stochastic dynamic games. We present a solver with polynomial-time iterations and conduct two experiments which show how robust belief space reasoning leads ego agents to proactively limit their future vulnerability to model misspecification of other agents' beliefs and actions, reducing performance degradation by over 48%.
| Subjects: | Multiagent Systems (cs.MA); Systems and Control (eess.SY) |
| Cite as: | arXiv:2610.40999 [cs.MA] |
| (or arXiv:2610.40999v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40999 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ryan Park [view email]
[v1]
Thu, 29 Oct 2026 21:30:36 UTC (637 KB)
来源：arXiv cs.MA · arxiv.org