Multi-agent Reinforcement Learning on SMAC 6h_vs_8z

Metric: Average Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Average Score▼	Augmentations	Paper	Date↕	Code
1	DDN	19.4	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
2	DPLEX	17.88	No	A Unified Framework for Factorizing Distribution...	2023-06-04	Code
3	DMIX	17.14	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
4	QPLEX	15.95	No	A Unified Framework for Factorizing Distribution...	2023-06-04	Code
5	VDN	15.41	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
6	DIQL	14.94	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
7	QMIX	14.37	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
8	IQL	13.78	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code

#1DDNSOTA
19.4
Average Score· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#2DPLEX
17.88
Average Score· 2023-06-04
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning Code
#3DMIX
17.14
Average Score· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#4QPLEX
15.95
Average Score· 2023-06-04
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning Code
#5VDN
15.41
Average Score· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#6DIQL
14.94
Average Score· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#7QMIX
14.37
Average Score· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#8IQL
13.78
Average Score· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code