期望自由能作为Bethe拉格朗日量的信息约束
Expected free energy as an information constraint on the Bethe Lagrangian
浏览论文内容
中文总结 AI 辅助
该研究提出受信息约束的Bethe拉格朗日量，可恢复主动推理的期望自由能解，经实验验证其在三个任务上的性能可与EFE和Q-MDP相媲美。
中文摘要 AI 辅助
主动推理通过最小化关于预测未来的期望自由能泛函来选择动作。然而，对尚未观测到的结果添加期望意味着自由能泛函不再具有Kullback-Leibler结构，这阻碍了推理过程的消息传递处理。我们提出一种基于Bethe自由能泛函的替代公式，完全支持通过消息传递进行推理。除了归一化、边缘化和形式约束外，我们还通过施加信息约束来维持认知驱动，该约束要求给定动作的未来观测、状态和参数之间的互信息必须至少等于目标先验的熵。对于相应的Karush-Kuhn-Tucker乘子的特定值，该受约束Bethe拉格朗日量的驻点可恢复期望自由能解。我们表明，随着信息需求的变化，求解得到的乘子会经过非激活、内部和饱和三种状态。在非激活状态下，智能体的认知驱动完全关闭；而在饱和状态下，认知驱动达到最大。我们在三个任务上将受约束Bethe智能体的性能与EFE和Q-MDP进行了比较。
英文摘要
Active inference selects actions by minimising an expected free energy functional over predicted futures. However, adding an expectation over yet-unobserved outcomes means the free energy functional no longer has a Kullback-Leibler structure, which hinders message passing treatments of inference procedures. We propose an alternative formulation based on a Bethe free energy functional, fully supporting inference by message passing. The epistemic drive is maintained by imposing an information constraint, next to normalisation, marginalisation and form constraints, insisting that the mutual information between future observations, states and parameters given actions must be at least as large as the entropy of the goal prior. For a specific value of the corresponding Karush-Kuhn-Tucker multiplier, the stationary point of this constrained Bethe Lagrangian recovers the expected free energy solution. We show that, as the information demand is varied, the solved multiplier moves through its inactive, interior, and saturated regimes. In the inactive regime the agent's epistemic drive switches off entirely, while in the saturated regime it is maximal. We compare the performance of the constrained Bethe agent on three tasks against EFE and Q-MDP.
发表机构
- TU Eindhoven（埃因霍温理工大学）
机构由 AI 辅助整理，请以论文原文为准。
