AI Paper Atlas

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

A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning

Wei-Fang Sun, Cheng-Kuang Lee, Simon See, Chun-Yi Lee

JMLR 2023 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Value factorization · 1 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
replace expected-value learner with distributional IQN learner (DIQL)IQL · SMAC 3s5z_vs_3s6zmedian win rate (%): 29.83 -> 62.22Improved
replace expected-value learner with distributional IQN learner (DIQL)IQL · SMAC 27m_vs_30mmedian win rate (%): 2.27 -> 6.02Improved
replace expected-value learner with distributional IQN learner (DIQL)IQL · SMAC corridormedian win rate (%): 84.87 -> 91.62Improved
replace expected-value learner with distributional IQN learner (DIQL)IQL · SMAC 6h_vs_8zmedian win rate (%): 0.00 -> 0.00No clear effect
add DFAC (distributional factorization, DMIX)QMIX · SMAC 6h_vs_8zmedian win rate (%): 12.78 -> 49.43Improved
add DFAC (distributional factorization, DMIX)QMIX · SMAC corridormedian win rate (%): 37.61 -> 90.45Improved
add DFAC (distributional factorization, DPLEX)QPLEX · SMAC 6h_vs_8zmedian win rate (%): 0.00 -> 43.75Improved
add DFAC (distributional factorization, DPLEX)QPLEX · SMAC MMM2median win rate (%): 96.88 -> 96.88No clear effect
add DFAC (distributional factorization, DPLEX)QPLEX · SMAC 27m_vs_30mmedian win rate (%): 78.12 -> 90.62Improved
add DFAC (DDN, distributional VDN with IQN)VDN · SMAC 6h_vs_8zmedian win rate (%): 0.00 -> 83.92Improved
add DFAC (distributional factorization, DMIX)QMIX · SMAC Ultra Hard 26m_vs_30mmedian win rate (%): 62.78 -> 81.82Improved
add DFAC (distributional factorization, DPLEX)QPLEX · SMAC Ultra Hard 26m_vs_30mmedian win rate (%): 78.12 -> 59.38Hurt

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