SMAC on Def_Infantry_sequential

Metric: Median Win Rate (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Median Win Rate▼	Extra Data	Paper	Date↕	Code
1	MADDPG	100	No	Multi-Agent Actor-Critic for Mixed Cooperative-C...	2017-06-07	Code
2	DRIMA	100	No	-	-	-
3	QTRAN	100	No	QTRAN: Learning to Factorize with Transformation...	2019-05-14	Code
4	DMIX	100	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
5	QMIX	96.9	No	QMIX: Monotonic Value Function Factorisation for...	2018-03-30	Code
6	VDN	96.9	No	Value-Decomposition Networks For Cooperative Mul...	2017-06-16	Code
7	IQL	93.8	No	The StarCraft Multi-Agent Challenges+ : Learning...	2022-07-05	Code
8	DIQL	93.8	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
9	DDN	90.6	No	DFAC Framework: Factorizing the Value Function v...	2021-02-16	Code
10	MASAC	37.5	No	Decomposed Soft Actor-Critic Method for Cooperat...	2021-04-14	Code
11	COMA	28.1	No	Counterfactual Multi-Agent Policy Gradients	2017-05-24	Code

#1MADDPGSOTA
100
Median Win Rate· 2017-06-07
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments Code
#2DRIMA
100
Median Win Rate
No paper
#3QTRAN
100
Median Win Rate· 2019-05-14
QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning Code
#4DMIX
100
Median Win Rate· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#5QMIX
96.9
Median Win Rate· 2018-03-30
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning Code
#6VDN
96.9
Median Win Rate· 2017-06-16
Value-Decomposition Networks For Cooperative Multi-Agent Learning Code
#7IQL
93.8
Median Win Rate· 2022-07-05
The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions Code
#8DIQL
93.8
Median Win Rate· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#9DDN
90.6
Median Win Rate· 2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning Code
#10MASAC
37.5
Median Win Rate· 2021-04-14
Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning Code
#11COMASOTA
28.1
Median Win Rate· 2017-05-24
Counterfactual Multi-Agent Policy Gradients Code