# Reinforcement Learning in the Wild: Scalable RL Dispatching Algorithm Deployed in Ridehailing Marketplace

arXiv: https://arxiv.org/abs/2202.05118 · HTML: https://mlsanity.com/paper/2202.05118/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 16 references that are in the map.
- First posted on arXiv 10 Feb 2022.

## Builds on (most cited first, 6 of 6)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Deep Value-network Based Approach for Multi-Driver Order Dispatching](https://mlsanity.com/paper/2106.04493/) (2021)
- [Synthetic Difference in Differences](https://mlsanity.com/paper/1812.09970/) (2018)
- [Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning](https://mlsanity.com/paper/2103.04555/) (2021)
- [Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms](https://mlsanity.com/paper/2105.08791/) (2021)
- [Maximum Weight Online Matching with Deadlines](https://mlsanity.com/paper/1808.03526/) (2018)

## Built on by (most cited first, 11 of 11)

- [Hybrid Multi-agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems](https://mlsanity.com/paper/2212.07313/) (2022)
- [Learning-based Online Optimization for Autonomous Mobility-on-Demand Fleet Control](https://mlsanity.com/paper/2302.03963/) (2023)
- [Global Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems](https://mlsanity.com/paper/2312.08884/) (2023)
- [BMG-Q: Localized Bipartite Match Graph Attention Q-Learning for Ride-Pooling Order Dispatch](https://mlsanity.com/paper/2501.13448/) (2025)
- [HCRide: Harmonizing Passenger Fairness and Driver Preference for Human-Centered Ride-Hailing](https://mlsanity.com/paper/2508.04811/) (2025)
- [Coordinating Ride-Pooling with Public Transit using Reward-Guided Conservative Q-Learning: An Offline Training and Online Fine-Tuning Reinforcement Learning Framework](https://mlsanity.com/paper/2501.14199/) (2025)
- [Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning](https://mlsanity.com/paper/2302.14833/) (2023)
- [LLM-ODDR: A Large Language Model Framework for Joint Order Dispatching and Driver Repositioning](https://mlsanity.com/paper/2505.22695/) (2025)
- [A Unified Representation Framework for Rideshare Marketplace Equilibrium and Efficiency](https://mlsanity.com/paper/2302.14358/) (2023)
- [Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems](https://mlsanity.com/paper/2510.10644/) (2025)
- [Adaptive Value Decomposition: Coordinating a Varying Number of Agents in Urban Systems](https://mlsanity.com/paper/2602.13309/) (2026)

## Abstract (arXiv)

In this study, a real-time dispatching algorithm based on reinforcement learning is proposed and for the first time, is deployed in large scale. Current dispatching methods in ridehailing platforms are dominantly based on myopic or rule-based non-myopic approaches. Reinforcement learning enables dispatching policies that are informed of historical data and able to employ the learned information to optimize returns of expected future trajectories. Previous studies in this field yielded promising results, yet have left room for further improvements in terms of performance gain, self-dependency, transferability, and scalable deployment mechanisms. The present study proposes a standalone RL-based dispatching solution that is equipped with multiple mechanisms to ensure robust and efficient on-policy learning and inference while being adaptable for full-scale deployment. A new form of value updating based on temporal difference is proposed that is more adapted to the inherent uncertainty of the problem. For the driver-order assignment, a customized utility function is proposed that when tuned based on the statistics of the market, results in remarkable performance improvement and interpretability. In addition, for reducing the risk of cancellation after drivers' assignment, an adaptive graph pruning strategy based on the multi-arm bandit problem is introduced. The method is evaluated using offline simulation with real data and yields notable performance improvement. In addition, the algorithm is deployed online in multiple cities under DiDi's operation for A/B testing and is launched in one of the major international markets as the primary mode of dispatch. The deployed algorithm shows over 1.3% improvement in total driver income from A/B testing. In addition, by causal inference analysis, as much as 5.3% improvement in major performance metrics is detected after full-scale deployment.