Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Smac On Smac 3S5Z Vs 3S6Z 1

Metrics

Median Win Rate

Results

Performance results of various models on this benchmark

Model Name	Median Win Rate	Paper Title	Repository
QMIX	2	Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
Heuristic	0	The StarCraft Multi-Agent Challenge
DIQL	62.22	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
QMIX	67.22	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
DDN	94.03	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
IQL	29.83	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
DMIX	91.08	DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
DPLEX	90.62	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
ACE	100	ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency
QPLEX	84.38	A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
VDN	2	The StarCraft Multi-Agent Challenge
IQL	0	The StarCraft Multi-Agent Challenge

0 of 13 row(s) selected.