Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Anytime Multi-Agent Path Finding via Machine Learning-Guided Large Neighborhood Search
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 a learned ranking function to choose agent sets for replanning instead of selecting one randomly | MAPF-LNS · den520d and city | AUC ratio (MAPF-LNS / method): 1.65±0.54; 1.75±0.41 | Helped |
| Train the ranking function on other grid maps rather than the test map | MAPF-ML-LNS · den520d and city | AUC ratio (MAPF-LNS / method): 1.31±0.30; 1.14±0.32 | Helped |
| Use the learned selector on the random map with 250 agents | MAPF-ML-LNS (ML-S) · random-32-32-10, 250 agents | AUC ratio (MAPF-LNS / method): 0.98±0.17 | Hurt |
| Train the ranking function on other maps and apply it to the random map with 250 agents | MAPF-ML-LNS (ML-O) · random-32-32-10, 250 agents | AUC ratio (MAPF-LNS / method): 0.95±0.12 | Hurt |
| Use learned agent-set ranking trained on fixed-agent-count instances | MAPF-ML-LNS · Grid maps with different agent counts from training | AUC ratio (MAPF-LNS / method) | Helped |
| Use the learned ranking function to select candidate agent sets rather than the sampling-based oracle | MAPF-LNS · random-32-32-10, 100 agents | runtime: 0.8 seconds; more than 16 seconds | Helped |
Closest papers by meaning
- Anytime Multi-Agent Path Finding with an Adaptive Delay-Based Heuristic (AAAI 2025 · similarity 0.94)
- Adaptive Anytime Multi-Agent Path Finding Using Bandit-Based Large Neighborhood Search (AAAI 2024 · similarity 0.94)
- Traffic Flow Optimisation for Lifelong Multi-Agent Path Finding (AAAI 2024 · similarity 0.91)
- Decentralized Monte Carlo Tree Search for Partially Observable Multi-Agent Pathfinding (AAAI 2024 · similarity 0.91)
- Learn to Follow: Decentralized Lifelong Multi-Agent Pathfinding via Planning and Learning (AAAI 2024 · similarity 0.91)
- LNS2+RL: Combining Multi-agent Reinforcement Learning with Large Neighborhood Search in Multi-agent Path Finding (AAAI 2025 · similarity 0.91)
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.