A Game-Theoretic Spatio-Temporal Reinforcement Learning Framework for Collaborative Public Resource Allocation

TL;DR

This paper introduces a game-theoretic reinforcement learning framework for collaborative public resource allocation, explicitly modeling capacity constraints and spatio-temporal dynamics to improve efficiency in real-world scenarios.

Contribution

It formulates CPRA as a potential game and develops GSTRL, a novel framework that captures spatio-temporal dynamics and approximates Nash equilibrium for NP-hard problems.

Findings

GSTRL outperforms baseline methods on real-world datasets.

Theoretical proof of no gap between potential function and optimal target.

Effective modeling of capacity constraints and dynamics in resource allocation.

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.