Research map / Multi-agent systems and games / Cooperative multi-agent RL
GRIP: Latent Field-Guided Graph Policy for Budget-Constrained Multi-Agent Routing
Yujiao Hu, Zuyu Chen, MengJie Lee, Jinchao Chen, Meng Shen, Hailun Zhang, Wei Li, Yan Pan
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 |
|---|---|---|---|
| add learned graph assignment (Stages I-II) to pruning plus reinsertion (ablation) | GRIP · Synthetic <5,50> | total reward R: 14.067 -> 17.329 | Improved |
| add Stage IV field-gradient reinsertion to assignment plus pruning (ablation) | GRIP · Synthetic <5,100> | total reward R: 26.084 -> 28.696 | Improved |
| add reinsertion/policy feedback to pruning-only variant (ablation) | GRIP-S3 · Synthetic <5,100> | total reward R: 9.157 -> 22.842 | Improved |
| use GRIP instead of Greedy baseline | MSS-BCR solver · Synthetic <10,100> | total reward R: 41.545 -> 45.442 | Improved |
| use GRIP out of training scale | MSS-BCR solver · Synthetic GT <20,1000> | total reward R: 338.740 -> 367.544 | Improved |
| use GRIP instead of Greedy on real city data | MSS-BCR solver · Denver <10,500> | total reward R: 413431 -> 437612 | Improved |
| use GRIP instead of Greedy on small real-city scale | MSS-BCR solver · Seattle <10,100> | total reward R: 277924 -> 278549 | Improved |
Closest papers by meaning
- Dynamic Latent Routing (NeurIPS 2026 · similarity 0.85)
- Adaptive Anytime Multi-Agent Path Finding Using Bandit-Based Large Neighborhood Search (AAAI 2024 · similarity 0.84)
- LNS2+RL: Combining Multi-agent Reinforcement Learning with Large Neighborhood Search in Multi-agent Path Finding (AAAI 2025 · similarity 0.84)
- Online Guidance Graph Optimization for Lifelong Multi-Agent Path Finding (AAAI 2025 · similarity 0.84)
- One Step is Enough: Multi-Agent Reinforcement Learning Based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms (NeurIPS 2026 · similarity 0.84)
- Learn to Follow: Decentralized Lifelong Multi-Agent Pathfinding via Planning and Learning (AAAI 2024 · similarity 0.84)
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.
