# Pattern Transfer Learning for Reinforcement Learning in Order Dispatching

arXiv: https://arxiv.org/abs/2105.13218 · HTML: https://mlsanity.com/paper/2105.13218/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 31 references that are in the map.
- First posted on arXiv 27 May 2021.

## Builds on (most cited first, 7 of 7)

- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [Transfer Learning in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2009.07888/) (2020)
- [Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning](https://mlsanity.com/paper/1703.02949/) (2017)
- [Distilling Policy Distillation](https://mlsanity.com/paper/1902.02186/) (2019)
- [Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1901.11454/) (2019)
- [Control of Robotic Mobility-On-Demand Systems: a Queueing-Theoretical Perspective](https://mlsanity.com/paper/1404.4391/) (2014)
- [Graph-Based Equilibrium Metrics for Dynamic Supply-Demand Systems with Applications to Ride-sourcing Platforms](https://mlsanity.com/paper/2102.05805/) (2021)

## Built on by (most cited first, 4 of 4)

- [Multi-Agent Transfer Learning in Reinforcement Learning-Based Ride-Sharing Systems](https://mlsanity.com/paper/2112.00424/) (2021)
- [Combining Experimental and Historical Data for Policy Evaluation](https://mlsanity.com/paper/2406.00317/) (2024)
- [Doubly Inhomogeneous Reinforcement Learning](https://mlsanity.com/paper/2211.03983/) (2022)
- [Designing Time Series Experiments in A/B Testing with Transformer Reinforcement Learning](https://mlsanity.com/paper/2602.01853/) (2026)

## Abstract (arXiv)

Order dispatch is one of the central problems to ride-sharing platforms. Recently, value-based reinforcement learning algorithms have shown promising performance on this problem. However, in real-world applications, the non-stationarity of the demand-supply system poses challenges to re-utilizing data generated in different time periods to learn the value function. In this work, motivated by the fact that the relative relationship between the values of some states is largely stable across various environments, we propose a pattern transfer learning framework for value-based reinforcement learning in the order dispatch problem. Our method efficiently captures the value patterns by incorporating a concordance penalty. The superior performance of the proposed method is supported by experiments.