HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Smac On Smac Off Complicated Parallel

Metrics

Median Win Rate

Results

Performance results of various models on this benchmark

Model Name
Median Win Rate
Paper TitleRepository
IQL35.0--
MASAC0.0Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning-
DRIMA100Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning-
DMIX0.0DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning-
QMIX0.0QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning-
COMA0.0Counterfactual Multi-Agent Policy Gradients-
DDN0.0DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning-
VDN70.0Value-Decomposition Networks For Cooperative Multi-Agent Learning-
DIQL0.0DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning-
QTRAN0.0QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning-
0 of 10 row(s) selected.
Smac On Smac Off Complicated Parallel | SOTA | HyperAI