AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning

Nicolas Carion, Nicolas Usunier, Gabriel Synnaeve, Alessandro Lazaric

NeurIPS 2019 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Decentralized actor-critic MARL · 12 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use quadratic rather than greedy assignment with the direct scoring model (ablation)Search and Rescue · 8×15, trained on 2×4average steps: 11.06 -> 7.85Improved
Use quadratic rather than linear-program assignment with the direct scoring model (ablation)Search and Rescue · 8×15, trained on 2×4average steps: 9.71 -> 7.85Improved
Use direct scoring instead of positional embeddings (ablation)Quad assignment · Search and Rescue, train 2×4, test 8×15average steps: 10.3 -> 7.85Improved
Use quadratic assignment instead of LP assignment (ablation)StarCraft Wraiths · w60v67, trained on w15v17win rate: 0.33 -> 0.72Improved
Use quadratic assignment instead of greedy assignment (ablation)StarCraft Wraiths · w60v67, trained on w15v17win rate: 0.13 -> 0.72Improved
Use quadratic assignment instead of LP assignment (ablation)StarCraft Marines · m30v30, trained on m10v10win rate: 0.74 -> 0.06Hurt
Use quadratic assignment instead of LP assignment (ablation)StarCraft Zergling-Hydralisk · zh10v12, trained on zh10v10win rate: 0.06 -> 0.01Hurt
Use positional-embedding scoring rather than direct scoring (ablation)AMax assignment · Search and Rescue, train 2×4, test 8×15average steps: 11.06 -> 15.8Hurt
Add capacity constraints to assignment (ablation)Search and Rescue · 8×15, trained on 2×4average steps: 11.06 -> 9.71Improved
Add quadratic task-task coordination scores to LP assignment (ablation)StarCraft Wraiths · w15v17, trained on w15v17win rate: 0.53 -> 0.89Improved

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