Transform-Invariant Generative Ray Path Sampling for Efficient Radio Propagation Modeling

2026-03-02

AI Summary

Ray tracing in radio propagation modeling suffers from prohibitive computational costs due to the exponential growth of candidate paths with interaction order, hindering its applicability in large-scale or real-time scenarios. This work proposes a novel approach that introduces Generative Flow Networks (GFlowNets) to ray path sampling, replacing exhaustive search with intelligent sampling through an efficient learning framework incorporating experience replay, physics-informed action masking, and uniform exploration. The method effectively mitigates the sparse reward problem, ensures physical feasibility of generated paths, and significantly enhances generalization. Experimental results demonstrate that the proposed approach achieves up to 10× acceleration on GPU and up to 1000× on CPU compared to conventional exhaustive methods, while maintaining high coverage accuracy and successfully discovering complex propagation paths.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Motion and Path Planning

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Ray tracing has become a standard for accurate radio propagation modeling, but suffers from exponential computational complexity, as the number of candidate paths scales with the number of objects raised to the power of the interaction order. This bottleneck limits its use in large-scale or real-time applications, forcing traditional tools to rely on heuristics to reduce the number of path candidates at the cost of potentially reduced accuracy. To overcome this limitation, we propose a comprehensive machine-learning-assisted framework that replaces exhaustive path searching with intelligent sampling via Generative Flow Networks. Applying such generative models to this domain presents significant challenges, particularly sparse rewards due to the rarity of valid paths, which can lead to convergence failures and trivial solutions when evaluating high-order interactions in complex environments. To ensure robust learning and efficient exploration, our framework incorporates three key architectural components. First, we implement an \emph{experience replay buffer} to capture and retain rare valid paths. Second, we adopt a uniform exploratory policy to improve generalization and prevent the model from overfitting to simple geometries. Third, we apply a physics-based action masking strategy that filters out physically impossible paths before the model even considers them. As demonstrated in our experimental validation, the proposed model achieves substantial speedups over exhaustive search -- up to $10\times$ faster on GPU and $1000\times$ faster on CPU -- while maintaining high coverage accuracy and successfully uncovering complex propagation paths. The complete source code, tests, and tutorial are available at https://github.com/jeertmans/sampling-paths.

Problem

• ray tracing
• radio propagation modeling
• computational complexity
• path sampling
• exponential complexity

Innovation

• Generative Flow Networks
• Ray Tracing
• Experience Replay
• Physics-based Action Masking
• Transform-Invariant Sampling