A Unifying Perspective on Causal World Models: From Observations to Representations to Structure· 因果世界模型的统一视角
World Models (WM) are increasingly seen as a foundation for intelligent agents that can predict, plan, and act beyond their training distribution. In this paper, we study WMs from a causal perspective across multiple levels of abstraction, ranging from perceptual observations to building a conceptual representation of the structure governing the environment dynamics. We argue that useful WMs must go beyond generative capabilities alone: they should also capture entity properties, entity-to-entity interactions, and entity-to-environment interactions that determine and explain the dynamics of a system. We provide a formal definition of Causal WMs (CWMs) grounded in the tasks they are intended to support, connecting world modelling with existing work in causal representation learning, object-
从感知到概念，构建统一的因果世界模型。
- 核心方法
- 提出了一种形式化的因果世界模型定义，将世界模型与因果表示学习、对象识别等领域的现有工作联系起来，涵盖从观察数据到抽象结构的多级抽象。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 传统的世界模型主要关注生成能力，未能充分捕捉和解释系统动力学中的实体属性、实体间交互及实体与环境交互。
- 关键实验
- 未提供
- 主要贡献
- 为构建更加智能、能够超越训练分布进行预测、规划和行动的代理提供了一种新的理论框架。
- 意义与局限
- 该研究的意义在于为智能代理的设计提供了更坚实的理论基础，但其应用尚需进一步实验验证。