الرئيسية الأخبار أحدث الأوراق البحثية الدروس مجموعات البيانات الموسوعة SOTA نماذج LLM لوحة الأداء GPU الفعاليات

العربية

Smac On Smac Off Near Parallel

المقاييس

Median Win Rate

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Median Win Rate	Paper Title	Repository
QMIX	95.0	QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
DIQL	0.0	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
COMA	20.0	Counterfactual Multi-Agent Policy Gradients
DDN	0.0	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
QTRAN	0.0	QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning
IQL	5.0	-	-
DMIX	0.0	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
MASAC	0.0	Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning
VDN	90.0	Value-Decomposition Networks For Cooperative Multi-Agent Learning
DRIMA	95.0	Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning	-

0 of 10 row(s) selected.