OpenCodePapers

smac-on-smac-3s5z-vs-3s6z-1

SMAC
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeMedian Win RateAverage ScoreModelNameReleaseDate
ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency✓ Link100ACE2022-11-29
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning✓ Link94.0320.94DDN2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning✓ Link91.0819.7DMIX2021-02-16
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning✓ Link90.6220.27DPLEX2023-06-04
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning✓ Link89.219.75VDN2021-02-16
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning✓ Link84.3820.42QPLEX2023-06-04
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning✓ Link67.2220.16QMIX2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning✓ Link62.2217.52DIQL2021-02-16
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning✓ Link29.8316.54IQL2021-02-16
The StarCraft Multi-Agent Challenge✓ Link2VDN2019-02-11
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning✓ Link2QMIX2020-03-19
The StarCraft Multi-Agent Challenge✓ Link0IQL2019-02-11
The StarCraft Multi-Agent Challenge✓ Link0Heuristic2019-02-11
Check out how to contribute new results.