Amir Nadav, Tiomkin Stas, Langdon Angela
ArXiv. 2025 Aug 20:arXiv:2508.15013v1.
Purposeful behavior is a hallmark of natural and artificial intelligence. Its acquisition is often believed to rely on world models, comprising both descriptive (what is) and prescriptive (what is desirable) aspects that identify and evaluate state of affairs in the world, respectively. Canonical computational accounts of purposeful behavior, such as reinforcement learning, posit distinct components of a world model comprising a state representation (descriptive aspect) and a reward function (prescriptive aspect). However, an alternative possibility, which has not yet been computationally formulated, is that these two aspects instead co-emerge interdependently from an agent's goal. Here, we describe a computational framework of goal-directed state representation in cognitive agents, in which the descriptive and prescriptive aspects of a world model co-emerge from agent-environment interaction sequences, or experiences. Drawing on Buddhist epistemology, we introduce a construct of goal-directed, or telic, states, defined as classes of goal-equivalent experience distributions. Telic states provide a parsimonious account of goal-directed learning in terms of the statistical divergence between behavioral policies and desirable experience features. We review empirical and theoretical literature supporting this novel perspective and discuss its potential to provide a unified account of behavioral, phenomenological and neural dimensions of purposeful behaviors across diverse substrates.
有目的行为是自然智能和人工智能的一个标志。人们通常认为其习得依赖于世界模型，该模型包含描述性（是什么）和规定性（什么是可取的）两个方面，分别用于识别和评估世界中的事务状态。有目的行为的典型计算解释，如强化学习，假定世界模型有不同的组成部分，包括状态表示（描述性方面）和奖励函数（规定性方面）。然而，另一种尚未在计算上得到阐述的可能性是，这两个方面反而从智能体的目标中相互依存地共同出现。在这里，我们描述了认知智能体中目标导向状态表示的计算框架，其中世界模型的描述性和规定性方面从智能体与环境的交互序列或经验中共同出现。借鉴佛教认识论，我们引入了目标导向或目的论状态的概念，定义为目标等效经验分布的类别。目的论状态根据行为策略与期望经验特征之间的统计差异，对目标导向学习提供了一种简洁的解释。我们回顾了支持这一新观点的实证和理论文献，并讨论了其为跨不同基质的有目的行为的行为、现象学和神经维度提供统一解释的潜力。
