TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Models/MADDPG

MADDPG

Reported on 16 benchmarks across 2 tasks · 1 paper · 8 SOTA

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

Methodology8 results

  • Multi-agent Reinforcement LearningonOff_Near_sequential
    Median Win Rate· 2017-06-07
    75
    best: 93.8 (DRIMA)
    SOTA
    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive EnvironmentsarXiv:1706.02275
  • Multi-agent Reinforcement LearningonDef_Outnumbered_sequential
    Median Win Rate· 2017-06-07
    81.3
    best: 100 (DRIMA)
    SOTA
    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive EnvironmentsarXiv:1706.02275
  • Multi-agent Reinforcement LearningonDef_Armored_sequential
    Median Win Rate· 2017-06-07
    90.6
    best: 100 (DRIMA)
    SOTA
    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive EnvironmentsarXiv:1706.02275
  • Multi-agent Reinforcement LearningonDef_Infantry_sequential
    Median Win Rate· 2017-06-07
    100
    SOTA
    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive EnvironmentsarXiv:1706.02275
  • Multi-agent Reinforcement LearningonOff_Superhard_sequential
    Median Win Rate
    0
    best: 15.6 (DRIMA)
  • Multi-agent Reinforcement LearningonOff_Complicated_sequential
    Median Win Rate
    0
    best: 96.9 (DRIMA)
  • Multi-agent Reinforcement LearningonOff_Distant_sequential
    Median Win Rate
    0
    best: 100 (DRIMA)
  • Multi-agent Reinforcement LearningonOff_Hard_sequential
    Median Win Rate
    0
    best: 96.9 (QMIX)

Playing Games8 results

  • SMAConOff_Near_sequential
    Median Win Rate· 2017-06-07
    75
    best: 93.8 (DRIMA)
    SOTA
    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive EnvironmentsarXiv:1706.02275
  • SMAConDef_Outnumbered_sequential
    Median Win Rate· 2017-06-07
    81.3
    best: 100 (DRIMA)
    SOTA
    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive EnvironmentsarXiv:1706.02275
  • SMAConDef_Armored_sequential
    Median Win Rate· 2017-06-07
    90.6
    best: 100 (DRIMA)
    SOTA
    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive EnvironmentsarXiv:1706.02275
  • SMAConDef_Infantry_sequential
    Median Win Rate· 2017-06-07
    100
    SOTA
    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive EnvironmentsarXiv:1706.02275
  • SMAConOff_Superhard_sequential
    Median Win Rate
    0
    best: 15.6 (DRIMA)
  • SMAConOff_Complicated_sequential
    Median Win Rate
    0
    best: 96.9 (DRIMA)
  • SMAConOff_Distant_sequential
    Median Win Rate
    0
    best: 100 (DRIMA)
  • SMAConOff_Hard_sequential
    Median Win Rate
    0
    best: 96.9 (QMIX)