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/VDN

VDN

Reported on 79 benchmarks across 6 tasks · 6 papers · 27 SOTA

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

Methodology35 results

Multi-agent Reinforcement LearningonSMAC 3s5z_vs_3s6z
Median Win Rate· 2019-02-11
2
best: 100 (ACE)
SOTA
The StarCraft Multi-Agent Challenge arXiv:1902.04043
Multi-agent Reinforcement LearningonSMAC MMM2
Median Win Rate· 2019-02-11
1
best: 100 (ACE)
SOTA
The StarCraft Multi-Agent Challenge arXiv:1902.04043
Multi-agent Reinforcement LearningonOff_Hard_parallel
Median Win Rate· 2017-06-16
15
best: 80 (DRIMA)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
Multi-agent Reinforcement LearningonOff_Complicated_parallel
Median Win Rate· 2017-06-16
70
best: 100 (DRIMA)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
Multi-agent Reinforcement LearningonOff_Near_parallel
Median Win Rate· 2017-06-16
90
best: 95 (QMIX)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
Multi-agent Reinforcement LearningonDef_Armored_parallel
Median Win Rate· 2017-06-16
5
best: 90 (DMIX)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
Multi-agent Reinforcement LearningonOff_Distant_parallel
Median Win Rate· 2017-06-16
85
best: 95 (DRIMA)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
Multi-agent Reinforcement LearningonDef_Infantry_parallel
Median Win Rate· 2017-06-16
95
best: 100 (QTRAN)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
Multi-agent Reinforcement LearningonDef_Armored_sequential
Median Win Rate· 2017-06-16
96.9
best: 100 (DRIMA)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
Multi-agent Reinforcement LearningonSMAC 6h_vs_9z
Average Score· 2023-06-04
13.57
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
17.16
best: 19.65 (DDN)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
Multi-agent Reinforcement LearningonSMAC 3s5z_vs_4s6z
Median Win Rate· 2023-06-04
47.16
best: 89.77 (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
13.13
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
13.35
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
7.78
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
17.3
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
75
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
16.69
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
23.01
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
19.75
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
89.2
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
19.47
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
85.34
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
19.36
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
89.2
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
15.41
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 27m_vs_30m
Average Score· 2021-02-16
18.45
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
63.12
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 LearningonDef_Outnumbered_sequential
Median Win Rate· 2017-06-16
15.6
best: 100 (DRIMA)
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
Multi-agent Reinforcement LearningonDef_Infantry_sequential
Median Win Rate· 2017-06-16
96.9
best: 100 (MADDPG)
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
Multi-agent Reinforcement LearningonSMAC corridor_2z_vs_24zg
Median Win Rate
0
best: 41.19 (DDN)
Multi-agent Reinforcement LearningonSMAC 6h_vs_8z
Median Win Rate
0
best: 93.75 (ACE)
Multi-agent Reinforcement LearningonSMAC 6h_vs_8z
Median Win Rate
0
best: 93.75 (ACE)
Multi-agent Reinforcement LearningonDef_Outnumbered_parallel
Median Win Rate
0
best: 70 (DRIMA)
Multi-agent Reinforcement LearningonOff_Superhard_parallel
Median Win Rate
0

Playing Games35 results

SMAConSMAC 3s5z_vs_3s6z
Median Win Rate· 2019-02-11
2
best: 100 (ACE)
SOTA
The StarCraft Multi-Agent Challenge arXiv:1902.04043
SMAConSMAC MMM2
Median Win Rate· 2019-02-11
1
best: 100 (ACE)
SOTA
The StarCraft Multi-Agent Challenge arXiv:1902.04043
SMAConOff_Hard_parallel
Median Win Rate· 2017-06-16
15
best: 80 (DRIMA)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
SMAConOff_Complicated_parallel
Median Win Rate· 2017-06-16
70
best: 100 (DRIMA)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
SMAConOff_Near_parallel
Median Win Rate· 2017-06-16
90
best: 95 (QMIX)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
SMAConDef_Armored_parallel
Median Win Rate· 2017-06-16
5
best: 90 (DMIX)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
SMAConOff_Distant_parallel
Median Win Rate· 2017-06-16
85
best: 95 (DRIMA)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
SMAConDef_Infantry_parallel
Median Win Rate· 2017-06-16
95
best: 100 (QTRAN)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
SMAConDef_Armored_sequential
Median Win Rate· 2017-06-16
96.9
best: 100 (DRIMA)
SOTA
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
SMAConSMAC 6h_vs_9z
Average Score· 2023-06-04
13.57
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
17.16
best: 19.65 (DDN)
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
SMAConSMAC 3s5z_vs_4s6z
Median Win Rate· 2023-06-04
47.16
best: 89.77 (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
13.13
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
13.35
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
7.78
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
17.3
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
75
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
16.69
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
23.01
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
19.75
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
89.2
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
19.47
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
85.34
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
19.36
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
89.2
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
15.41
best: 19.4 (DDN)
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
18.45
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
63.12
best: 91.48 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConDef_Outnumbered_sequential
Median Win Rate· 2017-06-16
15.6
best: 100 (DRIMA)
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
SMAConDef_Infantry_sequential
Median Win Rate· 2017-06-16
96.9
best: 100 (MADDPG)
Value-Decomposition Networks For Cooperative Multi-Agent Learning arXiv:1706.05296
SMAConSMAC corridor_2z_vs_24zg
Median Win Rate
0
best: 41.19 (DDN)
SMAConSMAC 6h_vs_8z
Median Win Rate
0
best: 93.75 (ACE)
SMAConSMAC 6h_vs_8z
Median Win Rate
0
best: 93.75 (ACE)
SMAConDef_Outnumbered_parallel
Median Win Rate
0
best: 70 (DRIMA)
SMAConOff_Superhard_parallel
Median Win Rate
0

Computer Vision7 results

DenoisingonSIDD
PSNR (sRGB)· 2019-08-29
39.28
best: 40.39 (CGNet)
SOTA
Variational Denoising Network: Toward Blind Noise Modeling and Removal arXiv:1908.11314
DenoisingonSIDD
SSIM (sRGB)· 2019-08-29
0.956
best: 0.973 (NBNet)
SOTA
Variational Denoising Network: Toward Blind Noise Modeling and Removal arXiv:1908.11314
DenoisingonDND
PSNR (sRGB)· 2019-08-29
39.38
best: 40.594 (DualDn)
SOTA
Variational Denoising Network: Toward Blind Noise Modeling and Removal arXiv:1908.11314
DenoisingonDND
SSIM (sRGB)· 2019-08-29
0.952
best: 0.966 (DualDn)
Variational Denoising Network: Toward Blind Noise Modeling and Removal arXiv:1908.11314
Image ClassificationonCIFAR-10
Percentage correct· 2015-07-22
92.4
best: 99.5 (ViT-H/14)
Training Very Deep Networks arXiv:1507.06228
Image ClassificationonCIFAR-100
Percentage correct· 2015-07-22
67.8
best: 96.08 (EffNet-L2 (SAM))
Training Very Deep Networks arXiv:1507.06228
Image ClassificationonMNIST
Percentage error· 2015-07-22
0.5
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
Training Very Deep Networks arXiv:1507.06228

Medical4 results

Image DenoisingonSIDD
PSNR (sRGB)· 2019-08-29
39.28
best: 40.39 (CGNet)
SOTA
Variational Denoising Network: Toward Blind Noise Modeling and Removal arXiv:1908.11314
Image DenoisingonSIDD
SSIM (sRGB)· 2019-08-29
0.956
best: 0.973 (NBNet)
SOTA
Variational Denoising Network: Toward Blind Noise Modeling and Removal arXiv:1908.11314
Image DenoisingonDND
PSNR (sRGB)· 2019-08-29
39.38
best: 40.594 (DualDn)
SOTA
Variational Denoising Network: Toward Blind Noise Modeling and Removal arXiv:1908.11314
Image DenoisingonDND
SSIM (sRGB)· 2019-08-29
0.952
best: 0.966 (DualDn)
Variational Denoising Network: Toward Blind Noise Modeling and Removal arXiv:1908.11314

Adversarial4 results

3D ArchitectureonSIDD
PSNR (sRGB)· 2019-08-29
39.28
best: 40.39 (CGNet)
SOTA
Variational Denoising Network: Toward Blind Noise Modeling and Removal arXiv:1908.11314
3D ArchitectureonSIDD
SSIM (sRGB)· 2019-08-29
0.956
best: 0.973 (NBNet)
SOTA
Variational Denoising Network: Toward Blind Noise Modeling and Removal arXiv:1908.11314
3D ArchitectureonDND
PSNR (sRGB)· 2019-08-29
39.38
best: 40.594 (DualDn)
SOTA
Variational Denoising Network: Toward Blind Noise Modeling and Removal arXiv:1908.11314
3D ArchitectureonDND
SSIM (sRGB)· 2019-08-29
0.952
best: 0.966 (DualDn)
Variational Denoising Network: Toward Blind Noise Modeling and Removal arXiv:1908.11314