Multi-Agent Reinforcement Learning for Dynamic Mobility Resource Allocation with Hierarchical Adaptive Grouping

2025-07-27

AI Summary

To address supply-demand imbalance in urban dynamic mobility resources (e.g., shared bicycles), this paper proposes a hierarchical adaptive multi-agent reinforcement learning framework. To overcome two key challenges—difficulty in cross-region policy sharing and prohibitive memory overhead from large-scale parameter storage—the method introduces three innovations: (1) a trajectory-similarity-driven dynamic agent grouping mechanism enabling online policy merging/splitting; (2) a hierarchical information fusion architecture for scalable coordination; and (3) learnable ID embeddings for memory-efficient parameter sharing. Extensive experiments on over 1.2 million real-world bike trips in New York City demonstrate that the framework significantly improves vehicle availability and rebalancing efficiency, outperforming state-of-the-art baselines. It further exhibits strong generalizability across spatiotemporal regimes and scalability to large-scale urban networks.

Technology Category

• Multiagent Systems: Multiagent Learning
• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: The sharing economy

Abstract

Allocating mobility resources (e.g., shared bikes/e-scooters, ride-sharing vehicles) is crucial for rebalancing the mobility demand and supply in the urban environments. We propose in this work a novel multi-agent reinforcement learning named Hierarchical Adaptive Grouping-based Parameter Sharing (HAG-PS) for dynamic mobility resource allocation. HAG-PS aims to address two important research challenges regarding multi-agent reinforcement learning for mobility resource allocation: (1) how to dynamically and adaptively share the mobility resource allocation policy (i.e., how to distribute mobility resources) across agents (i.e., representing the regional coordinators of mobility resources); and (2) how to achieve memory-efficient parameter sharing in an urban-scale setting. To address the above challenges, we have provided following novel designs within HAG-PS. To enable dynamic and adaptive parameter sharing, we have designed a hierarchical approach that consists of global and local information of the mobility resource states (e.g., distribution of mobility resources). We have developed an adaptive agent grouping approach in order to split or merge the groups of agents based on their relative closeness of encoded trajectories (i.e., states, actions, and rewards). We have designed a learnable identity (ID) embeddings to enable agent specialization beyond simple parameter copy. We have performed extensive experimental studies based on real-world NYC bike sharing data (a total of more than 1.2 million trips), and demonstrated the superior performance (e.g., improved bike availability) of HAG-PS compared with other baseline approaches.

Problem

• Dynamic allocation of urban mobility resources (e.g., bikes, scooters)
• Adaptive policy sharing across multi-agent reinforcement learning systems
• Memory-efficient parameter sharing for large-scale urban settings

Innovation

• Hierarchical Adaptive Grouping-based Parameter Sharing
• Dynamic and adaptive agent grouping approach
• Learnable identity embeddings for agent specialization