arXiv cs.AI· Jianhong Wang, Jonathan Lawry·· 3 天前AI 评分15
多智能体系统中刻画智能体异质性的对称性研究
On Symmetry for Characterizing Agent Heterogeneity in Multi-Agent Systems
AI 导读
研究针对有限时域 POSG 提出"策略评估对称性"概念：当完整策略评估与某变换可交换时，该变换即为对称性，其智能体轨道定义了结构化的智能体类型，且分类不依赖具体策略或初始状态分布。研究证明逐分量环境自同构必为策略评估对称性，但逆命题不成立；在协作 Dec-POMDP 中，即使共享同一奖励，智能体也可属于不同结构类型。
正文 · 原文
Abstract:Understanding agent heterogeneity can inform the design of shared and agent-specific policy representations, however existing criteria provide no unified structural test. We study finite-horizon POSGs and define a type-compatible transformation as a policy-evaluation symmetry when complete policy evaluation commutes with it for every decentralized behavioral policy. Policy-evaluation symmetries form a group for which agent orbits define structural agent types. This classification does not depend on the particular policy chosen or the distribution of initial states. We prove that every componentwise environment automorphism is a policy-evaluation symmetry, but that the converse does not hold. Applying the framework to cooperative Dec-POMDPs shows that agents can belong to different structural types even when they share a common reward. For prescribed weighted reward aggregation, we derive an exact value identity and sufficient conditions for the resulting Dec-POMDP to inherit the policy-evaluation symmetries of the source POSG. Finally, we give sufficient conditions under which repeated model factorizations induce policy-evaluation symmetry, and show that preserving an optimal Boltzmann policy set neither implies nor follows from this symmetry in general.
| Comments: | 25 pages |
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18538 [cs.MA] |
| (or arXiv:2610.18538v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18538 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jianhong Wang [view email]
[v1]
Tue, 13 Oct 2026 15:19:59 UTC (145 KB)
来源：arXiv cs.AI · arxiv.org