用强化学习动态发现物体间因果关系，提升预测精度与效率
Causal Process Models: Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Problem
- 将因果图构建转化为多智能体强化学习问题，仅在交互时建立连接
- 在长时序和不同物体数量下，物理预测误差显著低于传统方法
- 通过三维度分解实现语义可解释的因果编码，适合动态系统建模
大多数神经因果模型假设因果图是静态的，无法捕捉物理交互中因果关系随时间变化且稀疏的特性。本文提出因果过程框架及其神经实现——因果过程模型（CPMs），用于从视觉观测中学习稀疏、时变的因果图。不同于维持稠密连接的传统方法，本模型仅在物体主动交互时显式构建因果边，大幅提高可解释性与计算效率。我们将其转化为多智能体强化学习问题，由专用智能体逐时决定哪些物体在当前时刻存在因果关联。核心创新在于一种结构化表征，将物体和力向量沿三个学习维度（可变性、因果相关性、控制相关性）分解，实现语义有意义的自动编码。实验表明，CPM在物理预测任务中显著优于稠密图基线，尤其在长时序预测和不同物体数量条件下表现更优。
原文摘要 · Abstract (English)
Most neural models of causality assume static causal graphs, failing to capture the dynamic and sparse nature of physical interactions where causal relationships emerge and dissolve over time. We introduce the Causal Process Framework and its neural implementation, Causal Process Models (CPMs), for learning sparse, time-varying causal graphs from visual observations. Unlike traditional approaches that maintain dense connectivity, our model explicitly constructs causal edges only when objects actively interact, dramatically improving both interpretability and computational efficiency. We achieve this by casting dynamic interaction-graph construction for world modeling as a multi-agent reinforcement learning problem, where specialized agents sequentially decide which objects are causally connected at each timestep. Our key innovation is a structured representation that factorizes object and force vectors along three learned dimensions (mutability, causal relevance, and control relevance), enabling the automatic discovery of semantically meaningful encodings. We demonstrate that a CPM significantly outperforms dense graph baselines on physical prediction tasks, particularly for longer horizons and varying object counts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。