HyperAI초신경

홈 뉴스 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Smac On Smac 27M Vs 30M

평가 지표

Average Score

Median Win Rate

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Average Score	Median Win Rate	Paper Title	Repository
DMIX	19.43	85.45	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
VDN	18.45	63.12	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
DIQL	14.45	6.02	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
QMIX	19.41	84.77	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
Heuristic	-	0	The StarCraft Multi-Agent Challenge
DDN	19.71	91.48	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
QPLEX	19.33	78.12	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
DPLEX	19.62	90.62	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
IQL	14.01	2.27	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
QMIX	-	49	The StarCraft Multi-Agent Challenge
QMIX	-	49	Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

0 of 11 row(s) selected.