HyperAIHyperAI
الرئيسيةالأخبارأحدث الأوراق البحثيةالدروسمجموعات البياناتالموسوعةSOTAنماذج LLMلوحة الأداء GPUالفعاليات
البحث
حول
HyperAIHyperAI

Smac On Smac Def Outnumbered Parallel

المقاييس

Median Win Rate

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
Median Win Rate
Paper TitleRepository
DIQL0.0DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning-
QMIX30.0QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning-
IQL0.0The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions-
DRIMA70.0Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning-
DMIX5.0DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning-
COMA0.0Counterfactual Multi-Agent Policy Gradients-
MASAC0.0Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning-
VDN0.0Value-Decomposition Networks For Cooperative Multi-Agent Learning-
DDN0.0DFAC 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 Def Outnumbered Parallel | SOTA | HyperAI