# Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?

arXiv: https://arxiv.org/abs/2510.03257 · HTML: https://mlsanity.com/paper/2510.03257/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 68 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [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)
- [QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1905.05408/) (2019)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- [Mean Field Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1802.05438/) (2018)
- [A Review of Cooperative Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/1908.03963/) (2019)
- [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)
- [Value-Decomposition Multi-Agent Actor-Critics](https://mlsanity.com/paper/2007.12306/) (2020)
- [A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment](https://mlsanity.com/paper/2312.01058/) (2023)
- [Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2106.00285/) (2021)
- [A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives](https://mlsanity.com/paper/2503.13415/) (2025)
- [Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG](https://mlsanity.com/paper/1811.07029/) (2018)
- [Hybrid Multi-agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems](https://mlsanity.com/paper/2212.07313/) (2022)
- [A Distributed Model-Free Ride-Sharing Approach for Joint Matching, Pricing, and Dispatching using Deep Reinforcement Learning](https://mlsanity.com/paper/2010.01755/) (2020)
- [Context-aware Communication for Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2312.15600/) (2023)
- [A Distributed Model-Free Algorithm for Multi-hop Ride-sharing using Deep Reinforcement Learning](https://mlsanity.com/paper/1910.14002/) (2019)
- [CrossFi: A Cross Domain Wi-Fi Sensing Framework Based on Siamese Network](https://mlsanity.com/paper/2408.10919/) (2024)
- [Global Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems](https://mlsanity.com/paper/2312.08884/) (2023)

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

- [Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus](https://mlsanity.com/paper/2604.13472/) (2026)
- [Aggregate in the Advantage, Not the Ratio: A Canonical-Form Analysis of Cooperative Multi-Agent Policy Optimization](https://mlsanity.com/paper/2607.17924/) (2026)
- [MobiWave: Dispatch-Oriented Graph Wavelets and Drift-Guided Selective Optimization for Autonomous Fleet Rebalancing](https://mlsanity.com/paper/2607.24365/) (2026)
- [Low-Interaction-Rank Learning: Unifying Multiplicative Dual-Encoder Heads](https://mlsanity.com/paper/2608.11661/) (2026)

## Abstract (arXiv)

On-demand ride-sharing platforms, such as Uber and Lyft, face the intricate real-time challenge of bundling and matching passengers-each with distinct origins and destinations-to available vehicles, all while navigating significant system uncertainties. Due to the extensive observation space arising from the large number of drivers and orders, order dispatching, though fundamentally a centralized task, is often addressed using Multi-Agent Reinforcement Learning (MARL). However, independent MARL methods fail to capture global information and exhibit poor cooperation among workers, while Centralized Training Decentralized Execution (CTDE) MARL methods suffer from the curse of dimensionality. To overcome these challenges, we propose Triple-BERT, a centralized Single Agent Reinforcement Learning (MARL) method designed specifically for large-scale order dispatching on ride-sharing platforms. Built on a variant TD3, our approach addresses the vast action space through an action decomposition strategy that breaks down the joint action probability into individual driver action probabilities. To handle the extensive observation space, we introduce a novel BERT-based network, where parameter reuse mitigates parameter growth as the number of drivers and orders increases, and the attention mechanism effectively captures the complex relationships among the large pool of driver and orders. We validate our method using a real-world ride-hailing dataset from Manhattan. Triple-BERT achieves approximately an 11.95% improvement over current state-of-the-art methods, with a 4.26% increase in served orders and a 22.25% reduction in pickup times. Our code, trained model parameters, and processed data are publicly available at the repository https://github.com/RS2002/Triple-BERT .