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/DMIX

DMIX

Reported on 62 benchmarks across 2 tasks · 2 papers · 10 SOTA

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

Methodology31 results

Multi-agent Reinforcement LearningonSMAC MMM2_7m2M1M_vs_8m4M1M
Median Win Rate· 2023-06-04
63.35
SOTA
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
92.33
SOTA
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
19.17
SOTA
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
81.82
SOTA
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
Multi-agent Reinforcement LearningonDef_Armored_parallel
Median Win Rate· 2021-02-16
90
SOTA
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonSMAC 6h_vs_9z
Average Score· 2023-06-04
13.73
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
18.61
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
83.52
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
16.24
best: 16.5 (DDN)
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
7.41
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
19.33
best: 19.45 (DDN)
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
19.7
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
91.08
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
19.66
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
90.45
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
19.87
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
95.11
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
17.14
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
49.43
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
19.43
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
85.45
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_Infantry_parallel
Median Win Rate· 2021-02-16
90
best: 100 (QTRAN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonDef_Outnumbered_parallel
Median Win Rate· 2021-02-16
5
best: 70 (DRIMA)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonDef_Armored_sequential
Median Win Rate· 2021-02-16
81.3
best: 100 (DRIMA)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
Multi-agent Reinforcement LearningonDef_Infantry_sequential
Median Win Rate· 2021-02-16
100
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
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_Near_parallel
Median Win Rate
0
best: 95 (QMIX)
Multi-agent Reinforcement LearningonOff_Distant_parallel
Median Win Rate
0
best: 95 (DRIMA)
Multi-agent Reinforcement LearningonOff_Superhard_parallel
Median Win Rate
0

Playing Games31 results

SMAConSMAC MMM2_7m2M1M_vs_8m4M1M
Median Win Rate· 2023-06-04
63.35
SOTA
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
92.33
SOTA
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
19.17
SOTA
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
81.82
SOTA
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning arXiv:2306.02430
SMAConDef_Armored_parallel
Median Win Rate· 2021-02-16
90
SOTA
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConSMAC 6h_vs_9z
Average Score· 2023-06-04
13.73
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
18.61
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
83.52
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
16.24
best: 16.5 (DDN)
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
7.41
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
19.33
best: 19.45 (DDN)
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
19.7
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
91.08
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
19.66
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
90.45
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
19.87
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
95.11
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
17.14
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
49.43
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
19.43
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
85.45
best: 91.48 (DDN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConDef_Infantry_parallel
Median Win Rate· 2021-02-16
90
best: 100 (QTRAN)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConDef_Outnumbered_parallel
Median Win Rate· 2021-02-16
5
best: 70 (DRIMA)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConDef_Armored_sequential
Median Win Rate· 2021-02-16
81.3
best: 100 (DRIMA)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
SMAConDef_Infantry_sequential
Median Win Rate· 2021-02-16
100
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning arXiv:2102.07936
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_Near_parallel
Median Win Rate
0
best: 95 (QMIX)
SMAConOff_Distant_parallel
Median Win Rate
0
best: 95 (DRIMA)
SMAConOff_Superhard_parallel
Median Win Rate
0