Approximate Inference for Stochastic Planning in Factored Spaces-猫眼课题宝

DOI：

10.48550/arxiv.2203.12139

发表时间：

2022-03

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Zhennan Wu;R. Khardon

随机规划可以减少到大的离散图形模型的概率推理，但推理的硬度需要使用近似方案。在本文中，我们认为，这样的应用程序可以解开沿着两个维度。第一个是理想化精确优化目标中的信息流方向，即，前向和后向推理。第二个是用于计算此目标的近似类型，例如，置信传播（BP）与平均场变分推理（MFVI）。这种新的分类使我们能够统一以前工作中大量孤立的工作，解释它们的联系和差异以及潜在的改进。大量的随机规划问题的实验评估表明，前向BP的优势，基于MFVI的几种算法。MFVI的实际局限性的分析激发了一种新的算法，折叠状态变分推理（CSVI），它提供了一个更紧密的近似，并实现了可比的规划性能与前向BP。

Stochastic planning can be reduced to probabilistic inference in large discrete graphical models, but hardness of inference requires approximation schemes to be used. In this paper we argue that such applications can be disentangled along two dimensions. The first is the direction of information flow in the idealized exact optimization objective, i.e., forward vs. backward inference. The second is the type of approximation used to compute this objective, e.g., Belief Propagation (BP) vs. mean field variational inference (MFVI). This new categorization allows us to unify a large amount of isolated efforts in prior work explaining their connections and differences as well as potential improvements. An extensive experimental evaluation over large stochastic planning problems shows the advantage of forward BP over several algorithms based on MFVI. An analysis of practical limitations of MFVI motivates a novel algorithm, collapsed state variational inference (CSVI), which provides a tighter approximation and achieves comparable planning performance with forward BP.

Approximate Inference for Stochastic Planning in Factored Spaces

文献摘要

相似文献