In an ideal setting for Bayesian agents, a perfect description of the rules of the environment (i.e., the objective observation model) is available, allowing them to reason through the Bayesian posterior to update their beliefs in an optimal way. But such an ideal setting hardly ever exists in the natural world, so agents have to make do with reasoning about how they should update their beliefs simultaneously. This introduces a number of related challenges for a number of research areas: (1) For Bayesian statistics, this deviation of the subjective model from the true data-generating mechanism is termed model misspecification in the literature. (2) For neuroscience, it introduces the necessity to model how the agents' belief updates (how they use evidence to update their belief) and how their belief changes over time. The current paper addresses these two challenges by (a) providing a general class of posteriors/belief updates called cut-posteriors of Bayesian networks that have a much greater expressivity, and (b) parameterizing the space of possible posteriors to make meta-learning (i.e., choosing the belief update from this space in a principled manner) possible. For (a), it is noteworthy that any cut-posterior has local computation only, making computation tractable for human or artificial agents. For (b), a Markov Chain Monte Carlo algorithm to perform such meta-learning will be sketched here, though it is only an illustration and but no means the only possible meta-learning procedure possible for the space of cut-posteriors. Operationally, this work gives a general algorithm to take in an arbitrary Bayesian network and output all possible cut-posteriors in the space.

翻译：对于贝叶斯智能体而言，理想情况下可获得环境规则的完美描述（即客观观测模型），使其能够通过贝叶斯后验进行推理，从而以最优方式更新信念。然而，自然界中几乎不存在这种理想情况，因此智能体必须同时推理应如何更新信念。这为多个研究领域带来了一系列关联挑战：（1）在贝叶斯统计学中，主观模型与真实数据生成机制的偏差被文献称为模型误设；（2）在神经科学中，这要求对智能体的信念更新方式（如何利用证据更新信念）及其信念随时间变化的动态进行建模。本文通过以下方法应对这两项挑战：（a）提出一类被称为“贝叶斯网络截断后验”的通用后验/信念更新类，其表达能力显著增强；（b）对可能后验空间进行参数化，使得元学习（即从该空间中以原则性方式选择信念更新）成为可能。针对（a），值得关注的是任何截断后验仅需局部计算，从而使人或人工智能体的计算易于处理。针对（b），本文将通过马尔可夫链蒙特卡洛算法概要说明如何执行此类元学习——尽管这仅为举例说明，绝非截断后验空间唯一可能的元学习流程。在操作层面，本工作提供了一种通用算法，可接受任意贝叶斯网络作为输入，并输出该空间中的所有可能截断后验。