Research map / Multi-agent systems and games / Cooperative multi-agent RL
MAPDP: Cooperative Multi-Agent Reinforcement Learning to Solve Pickup and Delivery Problems
Zefang Zong, Meng Zheng, Yong Li, Depeng Jin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Share decoder parameters across agents (ablation) | MAPDP · Random Dataset, 2N=20 | Cost: 24.99 -> 24.87 | Improved |
| Share decoder parameters across agents (ablation) | MAPDP · Random Dataset, 2N=50 | Cost: 53.61 -> 52.59 | Improved |
| Share decoder parameters across agents (ablation) | MAPDP · Random Dataset, 2N=100 | Cost: 89.78 -> 88.97 | Improved |
| Share decoder parameters across agents (ablation) | MAPDP · Real-World Dataset, 2N=20 | Cost: 639 -> 624 | Improved |
| Share decoder parameters across agents (ablation) | MAPDP · Real-World Dataset, 2N=50 | Cost: 943 -> 890 | Improved |
| Share decoder parameters across agents (ablation) | MAPDP · Real-World Dataset, 2N=100 | Cost: 1721 -> 1705 | Improved |
| Add communication embedding for other agents' states (ablation) | MAPDP · Random Dataset, 2N=20 | Cost: 26.89 -> 24.87 | Improved |
| Add communication embedding for other agents' states (ablation) | MAPDP · Random Dataset, 2N=50 | Cost: 68.78 -> 52.59 | Improved |
| Add communication embedding for other agents' states (ablation) | MAPDP · Random Dataset, 2N=100 | Cost: 108.12 -> 88.97 | Improved |
| Add communication embedding for other agents' states (ablation) | MAPDP · Real-World Dataset, 2N=20 | Cost: 731 -> 624 | Improved |
| Add communication embedding for other agents' states (ablation) | MAPDP · Real-World Dataset, 2N=50 | Cost: 1033 -> 890 | Improved |
| Add communication embedding for other agents' states (ablation) | MAPDP · Real-World Dataset, 2N=100 | Cost: 1896 -> 1705 | Improved |
Later papers that compared with this method
1 later accepted paper reports MAPDP as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Multi-Agent Pointer Transformer: Seq-to-Seq Reinforcement Learning for Multi-Vehicle Dynamic Pickup-Delivery Problems (AAAI 2026 · better on 5 of 5 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- N-agent Ad Hoc Teamwork (NeurIPS 2024 · similarity 0.85)
- MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale (AAAI 2025 · similarity 0.85)
- LNS2+RL: Combining Multi-agent Reinforcement Learning with Large Neighborhood Search in Multi-agent Path Finding (AAAI 2025 · similarity 0.85)
- 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)
- POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding (ICLR 2025 · similarity 0.85)
- DPN: Decoupling Partition and Navigation for Neural Solvers of Min-max Vehicle Routing Problems (ICML 2024 · similarity 0.85)
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.
