AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Multi-Agent Path Finding with Delay Probabilities

AAAI 2017 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Learning-guided MAPF search · 104 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use AME with MCPs rather than Push and SwapMAPF-DP solving · random 1, 35 agentsaverage makespan: 812.41 $\pm$ 0.40 -> 71.28 $\pm$ 0.34Helped
Use AME with MCPs rather than Push and SwapMAPF-DP solving · warehouse 1, 35 agentsaverage makespan: 1,399.14 $\pm$ 0.43 -> 124.18 $\pm$ 0.44Helped
Replace MCPs with Fully Synchronized Policies (ablation)AME · random 1average makespan: 71.28 $\pm$ 0.34 -> 140.29 $\pm$ 0.50Hurt
Replace MCPs with Fully Synchronized Policies (ablation)AME · warehouse 1average makespan: 124.18 $\pm$ 0.44 -> 219.63 $\pm$ 0.65Hurt
Use a non-robust policy that always issues GO commands instead of MCPs (ablation)AME · random 1average makespan: 71.28 $\pm$ 0.34 -> 67.82 $\pm$ 0.35No clear effect
Use a non-robust policy that always issues GO commands instead of MCPs (ablation)AME · warehouse 1average makespan: 124.18 $\pm$ 0.44 -> 122.42 $\pm$ 0.42No clear effect
Increase the number of agentsAME on 30x30 grids · 50 to 200 agentssolved (%): 0.94; 0.68; 0.10; 0Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy