Multi-agent Reinforcement Learning on SMAC 27m_vs_30m

Metric: Median Win Rate (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Median Win Rate▼	Augmentations	Paper	Date↕	Code
1	DDN	91.48	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
2	DPLEX	90.62	No	A Unified Framework for Factorizing Distribution...	2023-06-04	Code
3	DMIX	85.45	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
4	QMIX	84.77	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
5	QPLEX	78.12	No	A Unified Framework for Factorizing Distribution...	2023-06-04	Code
6	VDN	63.12	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
7	QMIX	49	No	Monotonic Value Function Factorisation for Deep ...	2020-03-19	Code
8	QMIX	49	No	Monotonic Value Function Factorisation for Deep ...	2020-03-19	Code
9	DIQL	6.02	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
10	IQL	2.27	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
11	Heuristic	0	No	-	-	Code

#1DDNSOTA
91.48
Median Win Rate· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#2DPLEX
90.62
Median Win Rate· 2023-06-04
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning Code
#3DMIX
85.45
Median Win Rate· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#4QMIX
84.77
Median Win Rate· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#5QPLEX
78.12
Median Win Rate· 2023-06-04
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning Code
#6VDN
63.12
Median Win Rate· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#7QMIXSOTA
49
Median Win Rate· 2020-03-19
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning Code
#8QMIX
49
Median Win Rate· 2020-03-19
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning Code
#9DIQL
6.02
Median Win Rate· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#10IQL
2.27
Median Win Rate· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#11Heuristic
0
Median Win Rate
No paperCode