将主动推理统一为变分推断，实现高效可扩展的不确定性决策。
Active Inference is a Subtype of Variational Inference
- 把主动推理的期望自由能最小化转化为变分推断框架
- 提出消息传递算法，在因子化状态马尔可夫决策过程上实现高效推理
- 适合需要平衡探索与利用的复杂决策系统研究者
不确定性下的自动化决策需权衡利用与探索。传统方法分别处理，依赖启发式；主动推理则通过期望自由能（EFE）最小化统一二者。但EFE最小化计算成本高，限制可扩展性。我们基于最新理论，将EFE最小化重铸为变分推断，正式统一了规划即推断框架，并揭示认知驱动为独特的熵贡献项。主要贡献是提出一种新型消息传递方案，用于该统一目标，在因子化状态马尔可夫决策过程（factored-state MDPs）中实现可扩展的主动推理，克服高维规划不可行性。
原文摘要 · Abstract (English)
Automated decision-making under uncertainty requires balancing exploitation and exploration. Classical methods treat these separately using heuristics, while Active Inference unifies them through Expected Free Energy (EFE) minimization. However, EFE minimization is computationally expensive, limiting scalability. We build on recent theory recasting EFE minimization as variational inference, formally unifying it with Planning-as-Inference and showing the epistemic drive as a unique entropic contribution. Our main contribution is a novel message-passing scheme for this unified objective, enabling scalable Active Inference in factored-state MDPs and overcoming high-dimensional planning intractability.
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。