HyperAI超神经

首页资讯最新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 6H Vs 8Z 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
IQL	0	The StarCraft Multi-Agent Challenge
VDN	0	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
Heuristic	0	The StarCraft Multi-Agent Challenge
DDN	83.92	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
QMIX	3	Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
QMIX	12.78	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
ACE	93.75	ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency
VDN	0	The StarCraft Multi-Agent Challenge
QPLEX	-	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
QMIX	3	The StarCraft Multi-Agent Challenge
DMIX	49.43	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
DPLEX	43.75	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
IQL	0	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
DIQL	0.00	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

0 of 14 row(s) selected.