HyperAI超神经

首页资讯论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Smac On Smac Mmm2 1

评估指标

Median Win Rate

评测结果

各个模型在此基准测试上的表现结果

模型名称	Median Win Rate	Paper Title	Repository
ACE	100	ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency
QMIX	69	The StarCraft Multi-Agent Challenge
DIQL	85.23	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
DPLEX	96.88	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
QMIX	69	Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
IQL	0	The StarCraft Multi-Agent Challenge
VDN	1	The StarCraft Multi-Agent Challenge
QMIX	92.44	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
VDN	89.2	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
IQL	68.92	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
Heuristic	0	The StarCraft Multi-Agent Challenge
DDN	97.22	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
DMIX	95.11	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
QPLEX	96.88	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning

0 of 14 row(s) selected.