# RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-Hailing

arXiv: https://arxiv.org/abs/2512.13727 · HTML: https://mlsanity.com/paper/2512.13727/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MoE in reinforcement learning and robotics, one of 12 directions in Mixture-of-experts.
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 13 Dec 2025.

## Placed in

- Mixture-of-experts / [MoE in reinforcement learning and robotics](https://mlsanity.com/moe/moe-in-reinforcement-learning-and-robotics/)
- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 24 of 24)

- [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)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction](https://mlsanity.com/paper/1811.05320/) (2018)
- [From Sparse to Soft Mixtures of Experts](https://mlsanity.com/paper/2308.00951/) (2023)
- [Reinforcement Learning for Combinatorial Optimization: A Survey](https://mlsanity.com/paper/2003.03600/) (2020)
- [Sample Efficient Actor-Critic with Experience Replay](https://mlsanity.com/paper/1611.01224/) (2016)
- [A Study on Overfitting in Deep Reinforcement Learning](https://mlsanity.com/paper/1804.06893/) (2018)
- [Mixtures of Experts Unlock Parameter Scaling for Deep RL](https://mlsanity.com/paper/2402.08609/) (2024)
- [Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models](https://mlsanity.com/paper/2406.06563/) (2024)
- [JetMoE: Reaching Llama2 Performance with 0.1M Dollars](https://mlsanity.com/paper/2404.07413/) (2024)
- [Reinforcement Learning for Ridesharing: An Extended Survey](https://mlsanity.com/paper/2105.01099/) (2021)
- [Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning](https://mlsanity.com/paper/2104.09122/) (2021)
- [No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO](https://mlsanity.com/paper/2405.00662/) (2024)
- [Mixture of Experts in a Mixture of RL settings](https://mlsanity.com/paper/2406.18420/) (2024)
- [ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for Long-Term Cross-City Mobility Prediction](https://mlsanity.com/paper/2410.14099/) (2024)
- [Real-Time Dispatching of Large-Scale Ride-Sharing Systems: Integrating Optimization, Machine Learning, and Model Predictive Control](https://mlsanity.com/paper/2003.10942/) (2020)
- [A dynamic multi-region MFD model for ride-sourcing with ridesplitting](https://mlsanity.com/paper/2211.14560/) (2022)
- [Timing the Match: A Deep Reinforcement Learning Approach for Ride-Hailing and Ride-Pooling Services](https://mlsanity.com/paper/2503.13200/) (2025)
- [Simulating the Integration of Urban Air Mobility into Existing Transportation Systems: A Survey](https://mlsanity.com/paper/2301.12901/) (2023)
- [Large Scale Multi-GPU Based Parallel Traffic Simulation for Accelerated Traffic Assignment and Propagation](https://mlsanity.com/paper/2406.08496/) (2024)

## Abstract (arXiv)

Ride-hailing platforms face the challenge of balancing passenger waiting times with overall system efficiency under highly uncertain supply-demand conditions. Adaptive delayed matching, which controls the holding intervals for batched sets of requests and vehicles, reveals an inherent trade-off between matching and pickup delays. The resulting environment with temporally varying request arrival patterns and dynamic congestion calls for more expressive networks with sufficient capacity to capture their non-stationarity. To address the limitations of existing methods that rely on shallow encoders that cannot capture dynamic supply-demand patterns and congestion effects, we introduce the Regime-Aware Spatio-Temporal Mixture-of-Experts (RAST-MoE) framework, which formalizes adaptive delayed matching as a regime-aware Markov Decision Process and equips RL agents with a self-attention MoE encoder. Instead of relying on a single monolithic network, our design allows different experts to specialize automatically in varying operational conditions, improving representation capacity while maintaining per-sample computation efficiency. Despite its modest size of only 12M parameters, our framework consistently outperforms strong baselines. On real-world Uber trajectory data from San Francisco, it reduces average matching delay by 10%, and pickup delay by 15%. In addition, it demonstrates robustness to unseen demand regimes, stable training behavior without reward hacking, and expert specialization to different regimes. This study shows the strength of MoE-enhanced RL for large-scale decision-making tasks with complex spatiotemporal dynamics.