# One Step is Enough: Multi-Agent Reinforcement Learning based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms

arXiv: https://arxiv.org/abs/2507.15351 · HTML: https://mlsanity.com/paper/2507.15351/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Builds on (most cited first, 28 of 28)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?](https://mlsanity.com/paper/2011.09533/) (2020)
- [Mean Field Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1802.05438/) (2018)
- [In Defense of the Unitary Scalarization for Deep Multi-Task Learning](https://mlsanity.com/paper/2201.04122/) (2022)
- [Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1901.11454/) (2019)
- [DeepPool: Distributed Model-free Algorithm for Ride-sharing using Deep Reinforcement Learning](https://mlsanity.com/paper/1903.03882/) (2019)
- [A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives](https://mlsanity.com/paper/2503.13415/) (2025)
- [Hybrid Multi-agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems](https://mlsanity.com/paper/2212.07313/) (2022)
- [Quantifying the benefits of vehicle pooling with shareability networks](https://mlsanity.com/paper/1310.2963/) (2013)
- [Global Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems](https://mlsanity.com/paper/2312.08884/) (2023)
- [Efficient Ridesharing Dispatch Using Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2006.10897/) (2020)
- [BMG-Q: Localized Bipartite Match Graph Attention Q-Learning for Ride-Pooling Order Dispatch](https://mlsanity.com/paper/2501.13448/) (2025)
- [Multi-Agent Reinforcement Learning with Hierarchical Coordination for Emergency Responder Stationing](https://mlsanity.com/paper/2405.13205/) (2024)
- [Optimality of Independently Randomized Symmetric Policies for Exchangeable Stochastic Teams with Infinitely Many Decision Makers](https://mlsanity.com/paper/2008.11570/) (2020)
- [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)
- [Optimizing Ride-Pooling Operations with Extended Pickup and Drop-Off Flexibility](https://mlsanity.com/paper/2503.08472/) (2025)

## Built on by (most cited first, 5 of 5)

- [Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent System](https://mlsanity.com/paper/2602.08335/) (2026)
- [Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?](https://mlsanity.com/paper/2510.03257/) (2025)
- [Few-Shot Learning for Dynamic Operations of Automated Electric Taxi Fleets under Evolving Charging Infrastructure: A Meta-Deep Reinforcement Learning Approach](https://mlsanity.com/paper/2601.21312/) (2026)
- [Stage Light is Sequence2: Multi-Light Control via Imitation Learning](https://mlsanity.com/paper/2605.03660/) (2026)
- [RideSkill: A Hierarchical Algorithm for Generalized Ride Sharing with LLM-Driven Automatic Evolution](https://mlsanity.com/paper/2609.02250/) (2026)

## Abstract (arXiv)

Order dispatch is a critical task in ride-sharing systems with Autonomous Vehicles (AVs), directly influencing efficiency and profits. Recently, Multi-Agent Reinforcement Learning (MARL) has emerged as a promising solution to this problem by decomposing the large state and action spaces among individual agents, effectively addressing the Curse of Dimensionality (CoD) in transportation market, which is caused by the substantial number of vehicles, passengers, and orders. However, conventional MARL-based approaches heavily rely on accurate estimation of the value function, which becomes problematic in large-scale, highly uncertain environments. To address this issue, we propose two novel methods that bypass value function estimation, leveraging the homogeneous property of AV fleets. First, we draw an analogy between AV fleets and groups in Group Relative Policy Optimization (GRPO), adapting it to the order dispatch task. By replacing the Proximal Policy Optimization (PPO) baseline with the group average reward-to-go, GRPO eliminates critic estimation errors and reduces training bias. Inspired by this baseline replacement, we further propose One-Step Policy Optimization (OSPO), demonstrating that the optimal policy can be trained using only one-step group rewards under a homogeneous fleet. Experiments on a real-world ride-hailing dataset show that both GRPO and OSPO achieve promising performance across all scenarios, efficiently optimizing pickup times and the number of served orders using simple Multilayer Perceptron (MLP) networks. Furthermore, OSPO outperforms GRPO in all scenarios, attributed to its elimination of bias caused by the bounded time horizon of GRPO. Our code, trained models, and processed data are provided at https://github.com/RS2002/OSPO .