Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Graph Attention-Guided Search for Dense Multi-Agent Pathfinding
Rishabh Jain, Keisuke Okumura, Michael Amir, Amanda Prorok
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 edge features (ablation) | MAGAT+ · POGEMA 3456 instances | success rate: 83.77% -> 92.33% | Improved |
| add PIBT collision shielding (ablation) | MAGAT+ · POGEMA 3456 instances | success rate: 62.70% -> 92.33% | Improved |
| add PIBT collision shielding (ablation) | MAPF-GPT (6M) · POGEMA 3456 instances | success rate: 50.09% -> 92.22% | Improved |
| add graph attention (ablation) | MAGAT+ · POGEMA 3456 instances | success rate: 38.89% -> 92.33% | Improved |
| use LaGAT instead of lacam3 | LaCAM · Dense Warehouse/Room/Maze | sum-of-costs / lower bound (30 s) | Improved |
| use LaGAT instead of lacam3 | LaCAM · ost003d (large sparse map) | sum-of-costs / lower bound | No clear effect |
| add map-specific fine-tuning and pre-training (ablation) | LaGAT · densest scenarios of three dense maps | success rate | Improved |
| add deadlock detection (ablation) | LaGAT · densest scenarios of three dense maps | sum of costs | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MAPF-GPT (6M) — MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale (AAAI 2025) · better on 1 of 1 shared result
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
- Decentralized Monte Carlo Tree Search for Partially Observable Multi-Agent Pathfinding (AAAI 2024 · similarity 0.90)
- MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale (AAAI 2025 · similarity 0.90)
- Learn to Follow: Decentralized Lifelong Multi-Agent Pathfinding via Planning and Learning (AAAI 2024 · similarity 0.90)
- Online Guidance Graph Optimization for Lifelong Multi-Agent Path Finding (AAAI 2025 · similarity 0.88)
- LNS2+RL: Combining Multi-agent Reinforcement Learning with Large Neighborhood Search in Multi-agent Path Finding (AAAI 2025 · similarity 0.88)
- Anytime Multi-Agent Path Finding with an Adaptive Delay-Based Heuristic (AAAI 2025 · similarity 0.87)
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.
