AI RESEARCH
Fully Dynamic Rebalancing in Dockless Bike-Sharing Systems via Deep Reinforcement Learning
arXiv CS.LG
•
ArXi:2605.14501v1 Announce Type: cross This paper proposes a fully dynamic Deep Reinforcement Learning (DRL) method for rebalancing dockless bike-sharing systems, overcoming the limitations of periodic, system-wide interventions. We model the service through a graph-based simulator and cast rebalancing as a Marko decision process. A DRL agent routes a single truck in real time, executing localized pick-up, drop-off, and charging actions guided by spatiotemporal criticality scores.