AI Paper Atlas

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

Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition

AAAI 2023 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Value factorization · 26 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
Add CIA to QMIXQMIX · SMAC 10m_vs_11mtest win rate: 0.89 -> 0.95Helped
Add CIA to QMIXQMIX · SMAC 2c_vs_64zgtest win rate: 0.91 -> 0.95Helped
Add CIA to QMIXQMIX · SMAC 7sztest win rate: 0.33 -> 0.29Hurt
Add CIA to QMIXQMIX · SMAC 6h_vs_8ztest win rate: 0.36 -> 0.49Helped
Add CIA to QMIXQMIX · SMAC corridortest win rate: 0.58 -> 0.80Helped
Add CIA to QMIXQMIX · SMAC 3s5z_vs_3s6ztest win rate: 0.38 -> 0.87Helped
Replace CIA loss with credit classification loss (CC loss) (ablation)QMIX · SMAC scenariosperformanceMixed
Randomly shuffle agent values entering the mixer during training (ablation)QMIX · SMAC case studiesperformanceNo clear effect

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