A Game-Theoretic Spatio-Temporal Reinforcement Learning Framework for Collaborative Public Resource Allocation
Songxin Lei, Qiongyan Wang, Yanchen Zhu, Hanyu Yao, Sijie Ruan, Weilin Ruan, Yuyu Luo, Huaming Wu, Yuxuan Liang
TL;DR
This work defines Collaborative Public Resource Allocation (CPRA), a capacity-aware, spatio-temporal resource-scheduling problem, and shows it is NP-hard. It then develops Game-Theoretic Spatio-Temporal Reinforcement Learning (GSTRL), framing CPRA as a potential game whose total crowd coverage serves as the global reward, enabling near-Nash convergence through centralized RL. The framework combines flow and agent embeddings, BiLSTM and Fourier Neural Operator-based spatio-temporal feature extraction, and an actor-critic training regime to optimize long-term coverage under constraints. Empirical results on two real-world datasets demonstrate that GSTRL consistently outperforms strong baselines and ablations, with significant gains across varying energy budgets and system scales, underscoring its practical value for urban resource management.
Abstract
Public resource allocation involves the efficient distribution of resources, including urban infrastructure, energy, and transportation, to effectively meet societal demands. However, existing methods focus on optimizing the movement of individual resources independently, without considering their capacity constraints. To address this limitation, we propose a novel and more practical problem: Collaborative Public Resource Allocation (CPRA), which explicitly incorporates capacity constraints and spatio-temporal dynamics in real-world scenarios. We propose a new framework called Game-Theoretic Spatio-Temporal Reinforcement Learning (GSTRL) for solving CPRA. Our contributions are twofold: 1) We formulate the CPRA problem as a potential game and demonstrate that there is no gap between the potential function and the optimal target, laying a solid theoretical foundation for approximating the Nash equilibrium of this NP-hard problem; and 2) Our designed GSTRL framework effectively captures the spatio-temporal dynamics of the overall system. We evaluate GSTRL on two real-world datasets, where experiments show its superior performance. Our source codes are available in the supplementary materials.