The ability to plan ahead efficiently is central for both living organisms and artificial systems. Model-based planning and prospection are widely studied in both cognitive neuroscience and artificial intelligence (AI), but from different perspectives--and with different desiderata in mind (biological realism versus scalability) that are difficult to reconcile. Here, we introduce a novel method to plan in large POMDPs--Active Inference Tree Search (AcT)--that combines the normative character and biological realism of a leading planning theory in neuroscience (Active Inference) and the scalability of tree search methods in AI. This unification is beneficial for both approaches. On the one hand, using tree searches enables the biologically grounded, first principle, method of active inference to be applied to large-scale problems. On the other hand, active inference provides a principled solution to the exploration-exploitation dilemma, which is often addressed heuristically in tree search methods. Our simulations show that AcT successfully navigates binary trees that are challenging for sampling-based methods, problems that require adaptive exploration, and the large POMDP problem 'Rocksample'--in which AcT approximates state-of-the-art POMDP solutions. Furthermore, we illustrate how AcT can be used to simulate neurophysiological responses (e.g., in the hippocampus and prefrontal cortex) of humans and other animals that solve large planning problems. These numerical analyses show that Active Tree Search is a principled realisation of neuroscientific and AI theories of planning, which offer both biological realism and scalability.
翻译:对活生物体和人工系统来说,有效提前规划的能力是关键。基于模型的规划和前景规划在认知神经科学和人工智能(AI)中都进行了广泛研究,但从不同的视角和不同的思维偏差(生物现实主义与伸缩性)中研究,难以调和。在这里,我们引入了一种新的方法,在大型POMDPs-感应推断树搜索(AcT)中进行规划,将神经科学(感应推断)中领先规划理论的规范性和生物现实主义以及AI中树木搜索方法的伸缩性结合起来。这种统一对两种方法都有好处。一方面,使用树搜索可以使生物基础、第一原则、积极推断方法应用于大规模问题。另一方面,积极的推论为探索-探索性两难提供了一种原则性的解决办法,在树前搜索方法中往往以超自然方式加以解决。我们的模拟表明,AcT在基于取样的方法、需要适应性研究的问题、以及大规模POMDP的内值(A-O-al-al-al-alational-al-al-al-alliversal-al-Procial-al-Procial-Procial-Ial-Procial-Procial-Proversal-Proversal-I)中,我们使用了这些解释-Procial-li-Procial-Proal-li-li-Proversal-li-Proal-Ima-li-li-I-I-Proversal-li-I-I-I-I-I-Proversal-I-I-Proversal-I-Proversal-Proversal-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-