用路径概率统一预测、规划与不确定性，揭示不可逆性是模型的计算资源。
A Path-Space Formulation of Prediction in World Models: From a Single Action to Prediction, Planning, and Irreversibility
- 将世界模型的预测视为未来轨迹的概率分布，而非单步条件分布。
- 发现注意力不对称程度与数据不可逆性正相关，对长时预测影响显著。
- 适合研究模型可解释性、生成建模与因果推理的学者参考。
我们提出一种基于路径空间的世界模型预测新范式。不同于传统的一步条件分布序列，世界模型隐含定义了未来轨迹的概率测度。在局部近似为马尔可夫过程时，该路径测度具有Onsager-Machlup形式。在此框架下，预测（最可能轨迹）、规划（约束优化）和不确定性（涨落）均作为单一作用泛函的操作实现。通过分解潜空间动力学为可逆与不可逆成分，我们从模型回放中引入熵产生成本的可操作度量。在小规模基于注意力的模型中，我们发现训练过程中注意力不对称性与数据不可逆性成比例增长。对学习到的注意力进行对称化会抑制熵产，并选择性削弱对不可逆动力学的长时预测能力，而保留松弛型预测性能。结果表明，不可逆性可能是预测性世界模型的重要计算资源。更普遍地，根本的预测对象应是未来路径的分布，而非状态本身。
原文摘要 · Abstract (English)
We propose a path-space formulation of prediction in AI world models. Rather than sequences of one-step conditional distributions, we argue that a world model implicitly defines a probability measure over future trajectories. In the local regime where latent dynamics admit an effective Markovian description, this path measure takes the Onsager-Machlup form. Within this framework, prediction (most probable trajectory), planning (constrained optimization), and uncertainty (fluctuations) emerge as operations on a single action functional. We decompose the latent dynamics into reversible and irreversible components and introduce operational measures of entropy production from model rollouts. In controlled small-scale attention-based models, we find that attention asymmetry is acquired during training in proportion to the irreversibility of the data. Symmetrizing the learned attention suppresses entropy production and selectively degrades long-horizon prediction of irreversible dynamics while preserving relaxational prediction. These results suggest that irreversibility may serve as a computational resource for predictive world models. More generally, the fundamental predictive object is a distribution over future paths rather than states.
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。