List your company

ResearchFormerly WizWand

Offline Multi-Agent Reinforcement Learning

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

SMAC 6h_vs_8z (good-poor)

11.88Average Score

5

Feb 26, 2026

Marine-Easy Medium-Replay

87.5Performance (3m)

4

Mar 13, 2026

Marine-Easy Medium-Expert

98.8Score (3m)

4

Mar 13, 2026

Marine-Easy Medium

85.6Performance (3m Map)

4

Mar 13, 2026

Marine-Easy Expert

100Score (3m)

4

Mar 13, 2026

SMAC Marine-Hard Medium-Replay

81.9Win Rate (3m)

4

Mar 13, 2026

SMAC Marine-Hard Medium

84.4Win Rate (3m)

4

Mar 13, 2026

Multi-agent MuJoCo HalfCheetah k=1 (e, m1, m2, e-m1, e-m2, m1-m2)

3,760.5Return

4

Feb 26, 2026