# Regime-Calibrated Fleet Repositioning with a Spatial Queue-Regret Decomposition

arXiv: https://arxiv.org/abs/2604.03883 · HTML: https://mlsanity.com/paper/2604.03883/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Builds on (most cited first, 9 of 9)

- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [On Wasserstein Two Sample Testing and Related Families of Nonparametric Tests](https://mlsanity.com/paper/1509.02237/) (2015)
- [Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction](https://mlsanity.com/paper/1802.08714/) (2018)
- [From Predictive to Prescriptive Analytics](https://mlsanity.com/paper/1402.5481/) (2014)
- [A Deep Value-network Based Approach for Multi-Driver Order Dispatching](https://mlsanity.com/paper/2106.04493/) (2021)
- [Control of Robotic Mobility-On-Demand Systems: a Queueing-Theoretical Perspective](https://mlsanity.com/paper/1404.4391/) (2014)
- [Data-Driven Model Predictive Control of Autonomous Mobility-on-Demand Systems](https://mlsanity.com/paper/1709.07032/) (2017)
- [A BCMP Network Approach to Modeling and Controlling Autonomous Mobility-on-Demand Systems](https://mlsanity.com/paper/1607.04357/) (2016)
- [RG-TTA: Regime-Guided Meta-Control for Test-Time Adaptation in Streaming Time Series](https://mlsanity.com/paper/2603.27814/) (2026)

## Abstract (arXiv)

Ride-hailing and autonomous mobility-on-demand operators reposition idle supply before future demand is fully observed. We study a retrieval-calibrated predict-then-optimize approach for this problem: historical demand regimes are matched to the current query block, combined into a calibrated demand prior, and passed to a fleet-balancing controller. The paper makes three contributions. First, we train a leakage-safe similarity gate whose objective penalizes demand error, pickup spatial mismatch, and queue shortage risk rather than retrieval rank alone. Second, we develop a spatial queue-regret decomposition for a stable queueing surrogate, linking demand-field error to wait through queueing sensitivity, allocator sensitivity, and Wasserstein pickup mismatch. Third, we evaluate learned retrieval and external-style rebalancing baselines in a common simulator. In the calibrated-demand gate experiment, across eight New York City scenarios and ten seeds, the spatial gate reduces mean wait to 82.3s, compared with 85.3s for hand-tuned similarity and 85.8s for a distributional-only baseline. In a separate replay-demand controller comparison, a scenario chance-MPC analog and a share-target transportation LP improve on Wen-style rebalancing (92.2s/92.2s vs. 100.1s), a reduced GPR chance-MPC comparator is intermediate at 94.4s, and an oracle MPC diagnostic is 91.3s.