HyperAI초신경

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

한국어

HyperAI초신경

Smac On Smac Def Infantry Sequential

평가 지표

Median Win Rate

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Median Win Rate	Paper Title	Repository
DRIMA	100	Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning	-
DIQL	93.8	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
DDN	90.6	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
DMIX	100	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
MADDPG	100	Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
QTRAN	100	QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning
IQL	93.8	The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions
QMIX	96.9	QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
COMA	28.1	Counterfactual Multi-Agent Policy Gradients
MASAC	37.5	Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning
VDN	96.9	Value-Decomposition Networks For Cooperative Multi-Agent Learning

0 of 11 row(s) selected.