执行噪声下的意图推理：在社会困境中区分偶然不确定性与认知不确定性
Intention Inference Under Execution Noise: Separating Aleatoric and Epistemic Uncertainty in Social Dilemmas
浏览论文内容
中文总结 AI 辅助
针对带噪声社会困境中标准MDP无法区分意图与行动错误导致过度报复的问题，提出POMDP-AIF框架，推导噪声阈值并通过实验验证其在特定博弈中意图推理的情境优势。
中文摘要 AI 辅助
在带噪声的社会困境中，意图行动在执行前会被随机干扰，因此观察到的背叛行为可能反映敌对意图，也可能是行动错误。标准马尔可夫决策过程（MDP）公式将执行的行动视为状态，从结构上排除了这种区分，导致系统性过度报复。我们引入部分可观察马尔可夫决策过程（POMDP）公式，将对手意图编码为隐状态，将执行的行动视为带噪声的观测，在主动推理（AIF）框架内求解，其代价函数分解为认知分量和实用分量，共同解决当前意图推理与意图演化学习问题。在带对称噪声的迭代囚徒困境中，我们推导了决定合作崩溃的关键噪声阈值，并将其与学习先验的不动点条件关联。实验表明，意图推理的价值具有情境依赖性：POMDP在对抗条件性合作对手时具有一致优势，但在噪声足够大时，相互意图推理会产生由信念驱动的关联崩溃。该优势仅适用于意图归因与决策相关的博弈。
英文摘要
In noisy social dilemmas, intended actions are stochastically corrupted before execution, so an observed defection may reflect hostile intent or action error. Standard Markov Decision Process (MDP) formulations treat executed actions as states, structurally precluding this distinction and causing systematic over-retaliation. We introduce a Partially Observable MDP (POMDP) formulation encoding opponent intentions as latent states and executed actions as noisy observations, solved within the active inference (AIF) framework with a cost function that decomposes into epistemic and pragmatic components that jointly address inferring current intent and learning how intent evolves. In the Iterated Prisoner's Dilemma with symmetric noise, we derive a critical noise threshold governing cooperation collapse, connecting it to a fixed-point condition on learned priors. Experiments reveal that the value of intention inference is context-dependent: the POMDP provides consistent advantages against conditionally cooperative opponents, but mutual intention inference under sufficient noise produces correlated belief-driven collapse. The advantage is specific to games where intent attribution is decision-relevant.
发表机构
- University of Cape Town（开普敦大学）
- Neuroscience Institute, University of Cape Town（开普敦大学神经科学研究所）
- National Institute for Theoretical & Computational Sciences, Stellenbosch（斯泰伦博斯理论与计算科学国家研究所）
- Institut National de la recherche scientifique, Montreal（魁北克国家科学研究院（蒙特利尔））
机构由 AI 辅助整理，请以论文原文为准。
