Research map / Learning theory and algorithms / Combinatorial and search optimization
Neural Approximate Dynamic Programming for On-Demand Ride-Pooling
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use NeurADP's learned future-value function instead of the myopic Baseline assignment | Ride-pool matching · NY Yellow Taxi; 1000 vehicles, capacity 4, pickup delay 120 | requests served: 109436 ± 3309.862 -> 161257.8 ± 2704.993 | Helped |
| Use NeurADP's learned future-value function instead of the myopic Baseline assignment | Ride-pool matching · NY Yellow Taxi; capacity 10, 1000 vehicles, pickup delay 300 | requests served: 220737.4 ± 5334.318 -> 266310 ± 13789.16 | Helped |
| Use NeurADP's learned future-value function instead of the myopic Baseline assignment | Ride-pool matching · NY Yellow Taxi; capacity 4, 3000 vehicles, pickup delay 300 | requests served: 300122.6 ± 16428.76 -> 318786.4 ± 19384.14 | Helped |
| Use NeurADP rather than ZAC or TBF-Complete with the paper's feasible-action generation | Ride-pool matching · NY Yellow Taxi; pickup delay 120 seconds | service rate | Hurt |
| Increase the number of vehicles | NeurADP versus Baseline · NY Yellow Taxi; capacity 4; pickup delay 300 | percentage improvement: 23.43928 ± 2.80972; 9.472499 ± 1.198605; 6.218725 ± 1.300478 | Mixed |
Closest papers by meaning
- Optimizing Ride-Pooling Operations with Extended Pickup and Drop-Off Flexibility (AAAI 2026 · similarity 0.88)
- One Step is Enough: Multi-Agent Reinforcement Learning Based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms (NeurIPS 2026 · similarity 0.85)
- Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems (NeurIPS 2025 · similarity 0.85)
- NondBREM: Nondeterministic Offline Reinforcement Learning for Large-Scale Order Dispatching (AAAI 2024 · similarity 0.84)
- GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching (AAAI 2025 · similarity 0.83)
- i-Rebalance: Personalized Vehicle Repositioning for Supply Demand Balance (AAAI 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.