AI Paper Atlas

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

Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

Tabish Rashid, Mikayel Samvelyan, Christian Schroeder de Witt, Gregory Farquhar, Jakob Foerster, Shimon Whiteson

JMLR 2020 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Value factorization · 568 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 monotonic state-conditioned mixing network (QMIX vs VDN)VDN · SMAC 3s5ztest win rate (%): 84 -> 97Improved
add monotonic mixing network (QMIX vs VDN)VDN · SMAC 2c_vs_64zgtest win rate (%): 21 -> 58Improved
add monotonic mixing network (QMIX vs VDN)VDN · SMAC MMM2test win rate (%): 1 -> 69Improved
add monotonic mixing network (QMIX vs VDN)VDN · SMAC 27m_vs_30mtest win rate (%): 0 -> 49Improved
use QMIX instead of VDNVDN · SMAC bane_vs_banetest win rate (%): 94 -> 85Hurt
use QMIX instead of VDNVDN · SMAC 3s_vs_5ztest win rate (%): 91 -> 87Hurt
add central state to VDN as a state-dependent bias (VDN-S) (ablation)VDN · SMAC 3s5z, 2c_vs_64zg, MMM2test win rateImproved
make mixing weights depend on state (QMIX vs QMIX-NS) (ablation)QMIX-NS · SMAC 3s5z, 2c_vs_64zg, MMM2test win rateImproved
add nonlinear final layer to mixing network (QMIX vs QMIX-Lin) (ablation)QMIX-Lin · SMAC 3s5z, 2c_vs_64zg, MMM2test win rateMixed
use off-policy value-based factorisation instead of on-policy COMACOMA · SMAC 14 scenariosmedian test win rateImproved
use QMIX instead of QTRANQTRAN · SMAC 3s5z and 2s3ztest win rateImproved

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