扩展了多智能体图模型，让其能处理不完全信息下的信念博弈。
Higher-Order Belief in Incomplete Information MAIDs
- 提出不完全信息MAID框架，支持多智能体对彼此信念的建模。
- 证明该模型与无共同先验的不完全信息广义博弈等价。
- 引入递归最优响应解法，更适合无共同信念的现实场景。
多智能体影响图（MAIDs）是表示智能体间策略互动的概率图模型，与展开式博弈（EFGs）等价，但结构更紧凑、信息更丰富。然而，传统MAIDs无法建模不完全信息场景——即智能体对游戏本身及彼此信念存在差异。本文提出不完全信息MAIDs（II-MAIDs），定义了无限与有限深度两类，并证明其与无共同先验的不完全信息广义博弈等价。通过该等价关系，II-MAIDs继承经典均衡概念，但指出此类解在无共同先验时往往不现实，因违反共同理性知识。为此，本文提出基于递归最优响应的新解法。文中以一个假设的AI评估场景为例，展示II-MAIDs的实际应用价值。
原文摘要 · Abstract (English)
Multi-agent influence diagrams (MAIDs) are probabilistic graphical models which represent strategic interactions between agents. MAIDs are equivalent to extensive form games (EFGs) but have a more compact and informative structure. However, MAIDs cannot, in general, represent settings of incomplete information -- wherein agents have different beliefs about the game being played, and different beliefs about each-other's beliefs. In this paper, we introduce incomplete information MAIDs (II-MAIDs). We define both infinite and finite-depth II-MAIDs and prove an equivalence relation to EFGs with incomplete information and no common prior over types. We prove that II-MAIDs inherit classical equilibria concepts via this equivalence, but note that these solution concepts are often unrealistic in the setting with no common prior because they violate common knowledge of rationality. We define a more realistic solution concept based on recursive best-response. Throughout, we describe an example with a hypothetical AI agent undergoing evaluation to illustrate the applicability of II-MAIDs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。