Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/QMIX

QMIX

Reported on 72 benchmarks across 2 tasks · 4 papers · 24 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology45 results

Multi-agent Reinforcement LearningonSMAC 6h_vs_9z
Median Win Rate· 2023-06-04
1.14
SOTA
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
Multi-agent Reinforcement LearningonSMAC corridor
Median Win Rate· 2020-03-19
1
best: 100 (ACE)
SOTA
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
Multi-agent Reinforcement LearningonSMAC MMM2
Median Win Rate· 2020-03-19
69
best: 100 (ACE)
SOTA
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
Multi-agent Reinforcement LearningonSMAC 6h_vs_8z
Median Win Rate· 2020-03-19
3
best: 93.75 (ACE)
SOTA
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
Multi-agent Reinforcement LearningonSMAC 27m_vs_30m
Median Win Rate· 2020-03-19
49
best: 91.48 (DDN)
SOTA
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
Multi-agent Reinforcement LearningonOff_Near_sequential
Median Win Rate· 2018-03-30
90.6
best: 93.8 (DRIMA)
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
Multi-agent Reinforcement LearningonOff_Complicated_sequential
Median Win Rate· 2018-03-30
87.5
best: 96.9 (DRIMA)
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
Multi-agent Reinforcement LearningonOff_Near_parallel
Median Win Rate· 2018-03-30
95
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
Multi-agent Reinforcement LearningonDef_Armored_parallel
Median Win Rate· 2018-03-30
75
best: 90 (DMIX)
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
Multi-agent Reinforcement LearningonOff_Distant_sequential
Median Win Rate· 2018-03-30
93.8
best: 100 (DRIMA)
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
Multi-agent Reinforcement LearningonDef_Outnumbered_parallel
Median Win Rate· 2018-03-30
30
best: 70 (DRIMA)
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
Multi-agent Reinforcement LearningonOff_Hard_sequential
Median Win Rate· 2018-03-30
96.9
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
Multi-agent Reinforcement LearningonSMAC 6h_vs_9z
Average Score· 2023-06-04
12.37
best: 16 (DDN)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
Multi-agent Reinforcement LearningonSMAC 3s5z_vs_4s6z
Average Score· 2023-06-04
13.09
best: 19.65 (DDN)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
Multi-agent Reinforcement LearningonSMAC MMM2_7m2M1M_vs_8m4M1M
Average Score· 2023-06-04
14.4
best: 16.5 (DDN)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
Multi-agent Reinforcement LearningonSMAC MMM2_7m2M1M_vs_8m4M1M
Median Win Rate· 2023-06-04
29.55
best: 63.35 (DMIX)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
Multi-agent Reinforcement LearningonSMAC corridor_2z_vs_24zg
Average Score· 2023-06-04
4.8
best: 11.1 (DDN)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
Multi-agent Reinforcement LearningonSMAC MMM2_7m2M1M_vs_9m3M1M
Average Score· 2023-06-04
19.01
best: 19.45 (DDN)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
Multi-agent Reinforcement LearningonSMAC MMM2_7m2M1M_vs_9m3M1M
Median Win Rate· 2023-06-04
88.64
best: 92.33 (DMIX)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
Multi-agent Reinforcement LearningonSMAC 26m_vs_30m
Average Score· 2023-06-04
18.23
best: 19.17 (DMIX)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
Multi-agent Reinforcement LearningonSMAC 26m_vs_30m
Median Win Rate· 2023-06-04
62.78
best: 81.82 (DMIX)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
Multi-agent Reinforcement LearningonSMAC 3s5z_vs_3s6z
Average Score· 2021-02-16
20.16
best: 20.94 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonSMAC 3s5z_vs_3s6z
Median Win Rate· 2021-02-16
67.22
best: 100 (ACE)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonSMAC corridor
Average Score· 2021-02-16
15.07
best: 20 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonSMAC corridor
Median Win Rate· 2021-02-16
37.61
best: 100 (ACE)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonSMAC MMM2
Average Score· 2021-02-16
19.42
best: 20.9 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonSMAC MMM2
Median Win Rate· 2021-02-16
92.44
best: 100 (ACE)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonSMAC 6h_vs_8z
Average Score· 2021-02-16
14.37
best: 19.4 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonSMAC 6h_vs_8z
Median Win Rate· 2021-02-16
12.78
best: 93.75 (ACE)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonSMAC 27m_vs_30m
Average Score· 2021-02-16
19.41
best: 19.71 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonSMAC 27m_vs_30m
Median Win Rate· 2021-02-16
84.77
best: 91.48 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonSMAC 3s5z_vs_3s6z
Median Win Rate· 2020-03-19
2
best: 100 (ACE)
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
Multi-agent Reinforcement LearningonSMAC corridor
Median Win Rate· 2020-03-19
1
best: 100 (ACE)
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
Multi-agent Reinforcement LearningonSMAC MMM2
Median Win Rate· 2020-03-19
69
best: 100 (ACE)
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
Multi-agent Reinforcement LearningonSMAC 6h_vs_8z
Median Win Rate· 2020-03-19
3
best: 93.75 (ACE)
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
Multi-agent Reinforcement LearningonSMAC 27m_vs_30m
Median Win Rate· 2020-03-19
49
best: 91.48 (DDN)
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
Multi-agent Reinforcement LearningonDef_Infantry_parallel
Median Win Rate· 2018-03-30
95
best: 100 (QTRAN)
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
Multi-agent Reinforcement LearningonDef_Infantry_sequential
Median Win Rate· 2018-03-30
96.9
best: 100 (MADDPG)
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
Multi-agent Reinforcement LearningonOff_Superhard_sequential
Median Win Rate
0
best: 15.6 (DRIMA)
Multi-agent Reinforcement LearningonOff_Hard_parallel
Median Win Rate
0
best: 80 (DRIMA)
Multi-agent Reinforcement LearningonDef_Outnumbered_sequential
Median Win Rate
0
best: 100 (DRIMA)
Multi-agent Reinforcement LearningonOff_Complicated_parallel
Median Win Rate
0
best: 100 (DRIMA)
Multi-agent Reinforcement LearningonOff_Distant_parallel
Median Win Rate
0
best: 95 (DRIMA)
Multi-agent Reinforcement LearningonDef_Armored_sequential
Median Win Rate
0
best: 100 (DRIMA)
Multi-agent Reinforcement LearningonOff_Superhard_parallel
Median Win Rate
0

Playing Games45 results

SMAConSMAC 6h_vs_9z
Median Win Rate· 2023-06-04
1.14
SOTA
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
SMAConSMAC corridor
Median Win Rate· 2020-03-19
1
best: 100 (ACE)
SOTA
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
SMAConSMAC MMM2
Median Win Rate· 2020-03-19
69
best: 100 (ACE)
SOTA
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
SMAConSMAC 6h_vs_8z
Median Win Rate· 2020-03-19
3
best: 93.75 (ACE)
SOTA
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
SMAConSMAC 27m_vs_30m
Median Win Rate· 2020-03-19
49
best: 91.48 (DDN)
SOTA
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
SMAConOff_Near_sequential
Median Win Rate· 2018-03-30
90.6
best: 93.8 (DRIMA)
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
SMAConOff_Complicated_sequential
Median Win Rate· 2018-03-30
87.5
best: 96.9 (DRIMA)
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
SMAConOff_Near_parallel
Median Win Rate· 2018-03-30
95
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
SMAConDef_Armored_parallel
Median Win Rate· 2018-03-30
75
best: 90 (DMIX)
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
SMAConOff_Distant_sequential
Median Win Rate· 2018-03-30
93.8
best: 100 (DRIMA)
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
SMAConDef_Outnumbered_parallel
Median Win Rate· 2018-03-30
30
best: 70 (DRIMA)
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
SMAConOff_Hard_sequential
Median Win Rate· 2018-03-30
96.9
SOTA
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
SMAConSMAC 6h_vs_9z
Average Score· 2023-06-04
12.37
best: 16 (DDN)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
SMAConSMAC 3s5z_vs_4s6z
Average Score· 2023-06-04
13.09
best: 19.65 (DDN)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
SMAConSMAC MMM2_7m2M1M_vs_8m4M1M
Average Score· 2023-06-04
14.4
best: 16.5 (DDN)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
SMAConSMAC MMM2_7m2M1M_vs_8m4M1M
Median Win Rate· 2023-06-04
29.55
best: 63.35 (DMIX)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
SMAConSMAC corridor_2z_vs_24zg
Average Score· 2023-06-04
4.8
best: 11.1 (DDN)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
SMAConSMAC MMM2_7m2M1M_vs_9m3M1M
Average Score· 2023-06-04
19.01
best: 19.45 (DDN)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
SMAConSMAC MMM2_7m2M1M_vs_9m3M1M
Median Win Rate· 2023-06-04
88.64
best: 92.33 (DMIX)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
SMAConSMAC 26m_vs_30m
Average Score· 2023-06-04
18.23
best: 19.17 (DMIX)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
SMAConSMAC 26m_vs_30m
Median Win Rate· 2023-06-04
62.78
best: 81.82 (DMIX)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
SMAConSMAC 3s5z_vs_3s6z
Average Score· 2021-02-16
20.16
best: 20.94 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConSMAC 3s5z_vs_3s6z
Median Win Rate· 2021-02-16
67.22
best: 100 (ACE)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConSMAC corridor
Average Score· 2021-02-16
15.07
best: 20 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConSMAC corridor
Median Win Rate· 2021-02-16
37.61
best: 100 (ACE)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConSMAC MMM2
Average Score· 2021-02-16
19.42
best: 20.9 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConSMAC MMM2
Median Win Rate· 2021-02-16
92.44
best: 100 (ACE)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConSMAC 6h_vs_8z
Average Score· 2021-02-16
14.37
best: 19.4 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConSMAC 6h_vs_8z
Median Win Rate· 2021-02-16
12.78
best: 93.75 (ACE)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConSMAC 27m_vs_30m
Average Score· 2021-02-16
19.41
best: 19.71 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConSMAC 27m_vs_30m
Median Win Rate· 2021-02-16
84.77
best: 91.48 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConSMAC 3s5z_vs_3s6z
Median Win Rate· 2020-03-19
2
best: 100 (ACE)
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
SMAConSMAC corridor
Median Win Rate· 2020-03-19
1
best: 100 (ACE)
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
SMAConSMAC MMM2
Median Win Rate· 2020-03-19
69
best: 100 (ACE)
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
SMAConSMAC 6h_vs_8z
Median Win Rate· 2020-03-19
3
best: 93.75 (ACE)
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
SMAConSMAC 27m_vs_30m
Median Win Rate· 2020-03-19
49
best: 91.48 (DDN)
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:2003.08839
SMAConDef_Infantry_parallel
Median Win Rate· 2018-03-30
95
best: 100 (QTRAN)
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
SMAConDef_Infantry_sequential
Median Win Rate· 2018-03-30
96.9
best: 100 (MADDPG)
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning arXiv:1803.11485
SMAConOff_Superhard_sequential
Median Win Rate
0
best: 15.6 (DRIMA)
SMAConOff_Hard_parallel
Median Win Rate
0
best: 80 (DRIMA)
SMAConDef_Outnumbered_sequential
Median Win Rate
0
best: 100 (DRIMA)
SMAConOff_Complicated_parallel
Median Win Rate
0
best: 100 (DRIMA)
SMAConOff_Distant_parallel
Median Win Rate
0
best: 95 (DRIMA)
SMAConDef_Armored_sequential
Median Win Rate
0
best: 100 (DRIMA)
SMAConOff_Superhard_parallel
Median Win Rate
0