The sum-product network (SPN) has been extended to model sequence data with the recurrent SPN (RSPN), and to decision-making problems with sum-product-max networks (SPMN). In this paper, we build on the concepts introduced by these extensions and present state-based recurrent SPMNs (S-RSPMNs) as a generalization of SPMNs to sequential decision-making problems where the state may not be perfectly observed. As with recurrent SPNs, S-RSPMNs utilize a repeatable template network to model sequences of arbitrary lengths. We present an algorithm for learning compact template structures by identifying unique belief states and the transitions between them through a state matching process that utilizes augmented data. In our knowledge, this is the first data-driven approach that learns graphical models for planning under partial observability, which can be solved efficiently. S-RSPMNs retain the linear solution complexity of SPMNs, and we demonstrate significant improvements in compactness of representation and the run time of structure learning and inference in sequential domains.

No abstract

This study aims to analyse the flow characteristics and drag profiles of six different fin geometries - clipped delta, swept, trapezoidal, elliptical, rectangular, and triangular - for subsonic, transonic, and supersonic flow at different Mach numbers. By comparing the aerodynamic characteristics of these fin variants, the research aims to identify the most efficient fin geometry for each Mach regime. This study will benefit missile designers in selecting the most suitable fin geometry for their mission by providing information on the efficiency of each fin geometry at different Mach numbers. The findings of this research will enable the development of more efficient and effective fins for missile models