AI Paper Atlas

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

Rethinking Individual Global Max in Cooperative Multi-Agent Reinforcement Learning

Yitian Hong, Yaochu Jin, Yang Tang

NeurIPS 2022 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Decentralized actor-critic MARL · 8 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
add IGM-DA (DAgger imitation) to QMIXQMIX · SMAC sight view 0, averagewin rate: 47.8 -> 68.9Improved
add IGM-DA to QPLEXQPLEX · SMAC sight view 0, averagewin rate: 41.0 -> 63.1Improved
add IGM-DA to DMIXDMIX · SMAC sight view 0, averagewin rate: 50.4 -> 67.0Improved
add IGM-DA to QMIXQMIX · 3s_vs_5zwin rate: 1.9 -> 43.9Improved
add IGM-DA to QPLEXQPLEX · MMM2win rate: 0.0 -> 55.4Improved
add IGM-DA to DMIXDMIX · MMM2win rate: 0.0 -> 46.2Improved
add IGM-DA to QPLEXQPLEX · 5m_vs_6mwin rate: 5.0 -> 38.9Improved
add IGM-DA to DMIXDMIX · 8m_vs_9mwin rate: 64.7 -> 64.4No clear effect
add IGM-DA to DMIXDMIX · 5m_vs_6mwin rate: 58.7 -> 59.0No clear effect
add IGM-DA to QMIXQMIX · 8mwin rate: 98.3 -> 99.2No clear effect
add IGM-DA to DMIXDMIX · 3s5zwin rate: 76.2 -> 91.7Improved
replace DAgger with Behavior Cloning (ablation)IGM-DA · MMM2win rateHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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

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