Priorelli Matteo, Stoianov Ivilin Peev
Institute of Cognitive Sciences and Technologies, National Research Council of Italy, 35137 Padova, Italy.
DIAG, Sapienza University of Rome, 00185 Roma, Italy.
Entropy (Basel). 2025 May 27;27(6):570. doi: 10.3390/e27060570.
To determine an optimal plan for complex tasks, one often deals with dynamic and hierarchical relationships between several entities. Traditionally, such problems are tackled with optimal control, which relies on the optimization of cost functions; instead, a recent biologically motivated proposal casts planning and control as an inference process. assumes that action and perception are two complementary aspects of life whereby the role of the former is to fulfill the predictions inferred by the latter. Here, we present an active inference approach that exploits discrete and continuous processing, based on three features: the representation of in relation to the objects of interest; the use of hierarchical relationships that enable the agent to easily interpret and flexibly expand its body schema for tool use; the definition of related to the agent's intentions, used to infer and plan with dynamic elements at different temporal scales. We evaluate this on a habitual task: reaching a moving object after having picked a moving tool. We show that the model can tackle the presented task under different conditions. This study extends past work on planning as inference and advances an alternative direction to optimal control.
为了确定复杂任务的最优计划，人们常常需要处理多个实体之间的动态和层次关系。传统上，此类问题通过最优控制来解决，最优控制依赖于成本函数的优化；相反，最近一种受生物学启发的提议将规划和控制视为一个推理过程。该提议假设行动和感知是生命的两个互补方面，其中前者的作用是实现由后者推断出的预测。在这里，我们提出一种主动推理方法，该方法基于三个特征利用离散和连续处理：与感兴趣对象相关的表示；使用层次关系，使智能体能够轻松解释并灵活扩展其用于工具使用的身体图式；与智能体意图相关的定义，用于在不同时间尺度上对动态元素进行推理和规划。我们在一个习惯性任务上评估了这种方法：拿起一个移动的工具后去够一个移动的物体。我们表明该模型可以在不同条件下处理所呈现的任务。这项研究扩展了过去关于将规划作为推理的工作，并推进了一条与最优控制不同的方向。
