HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Smac On Smac Mmm2 1

Metrics

Median Win Rate

Results

Performance results of various models on this benchmark

Model Name
Median Win Rate
Paper TitleRepository
ACE100ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency-
QMIX69The StarCraft Multi-Agent Challenge-
DIQL85.23DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning-
DPLEX96.88A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning-
QMIX69Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning-
IQL0The StarCraft Multi-Agent Challenge-
VDN1The StarCraft Multi-Agent Challenge-
QMIX92.44DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning-
VDN89.2DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning-
IQL68.92DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning-
Heuristic0The StarCraft Multi-Agent Challenge-
DDN97.22DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning-
DMIX95.11DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning-
QPLEX96.88A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning-
0 of 14 row(s) selected.
Smac On Smac Mmm2 1 | SOTA | HyperAI