arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.13860cs.AImath.PRq-bio.NC
收藏

大规模POMDPs中的主动推断树搜索

Active Inference Tree Search in Large POMDPs

Institute of Cognitive Sciences and Technologies, National Research Council(国家研究委员会认知科学与技术研究所);Institute for High Performance Computing and Networking, National Research Council(国家研究委员会高性能计算与网络研究所);University College London(伦敦大学学院);VERSES AI Research Lab(VERSES人工智能研究实验室)

Domenico Maisto, Francesco Gregoretti, Karl Friston, Giovanni Pezzulo

AI总结:

本文提出主动推断树搜索方法,结合神经科学与人工智能的规划理论,实现大规模POMDP问题的高效解决。

摘要:

高效前瞻性规划能力对于生物体和人工系统都至关重要。基于模型的规划和前瞻性在认知神经科学和人工智能(AI)中被广泛研究,但视角不同,目标也不同(生物真实性与可扩展性),难以调和。本文介绍了一种新的POMDP规划方法——主动推断树搜索(AcT),它结合了神经科学中领先的规划理论(主动推断)的规范特征和生物真实性,以及人工智能中树搜索方法的可扩展性。这种统一增强了两种方法。一方面,树搜索使基于生物基础的、第一原理的主动推断方法能够应用于大规模问题。另一方面,主动推断为探索-利用困境提供了原理性解决方案,而树搜索方法通常采用启发式方法解决。我们的模拟显示,AcT能够成功导航对基于采样方法具有挑战性的二进制树,解决需要适应性探索的问题,以及大规模POMDP问题'RockSample'——在该问题中,AcT重现了最先进的POMDP解决方案。此外,我们展示了如何利用AcT来模拟人类和其他动物在解决大规模规划问题时的神经生理反应(例如海马体和前额叶皮层)。这些数值分析表明,主动树搜索是神经科学和AI规划理论的原理性实现,既具有生物真实性又具有可扩展性。

英文摘要:

The ability to plan ahead efficiently is key for both living organisms and artificial systems. Model-based planning and prospection are widely studied in 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 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 enhances both approaches. On the one hand, tree searches enable 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 reproduces 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 planning theories, which offer both biological realism and scalability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑