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

العربية

Smac On Smac 26M Vs 30M

المقاييس

Average Score

Median Win Rate

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Average Score	Median Win Rate	Paper Title	Repository
VDN	16.69	23.01	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
QMIX	18.23	62.78	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
QPLEX	18.66	78.12	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
DMIX	19.17	81.82	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
DDN	18.49	67.90	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
DPLEX	18.49	59.38	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning

0 of 6 row(s) selected.