Multi-Agent Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
100Pass & Shoot Success Rate
5
May 21, 2026
0.001Avg KL Divergence
5
May 14, 2026
0.001Average KL Divergence
5
May 14, 2026
0.078Average KL Divergence
5
May 14, 2026
4,232Mean Episode Reward
5
May 11, 2026
4,532Mean Episode Reward
5
May 11, 2026
5,345Mean Episode Reward
5
May 11, 2026
5,176Mean Episode Reward
5
May 11, 2026
1,623.473Final Episode Return
5
Mar 17, 2026
430.1Parameters (K)
5
Mar 17, 2026
430.36Parameters (K)
5
Mar 17, 2026
430.36Params (K)
5
Mar 17, 2026
102.66Parameters (K)
5
Mar 17, 2026
101.77Parameters (K)
5
Mar 17, 2026
130.54Parameters (K)
5
Mar 17, 2026
124.36Params (K)
5
Mar 17, 2026
102.28Params (K)
5
Mar 17, 2026
191.18Number of learnable parameters (K)
5
Mar 17, 2026
80.625Median Win Rate
5
Mar 5, 2026
86.719Median Win Rate
5
Mar 5, 2026
71.484Median Win Rate
5
Mar 5, 2026
69.531Median Win Rate
5
Mar 5, 2026
60.078Median Win Rate
5
Mar 5, 2026
71.25Median Win Rate
5
Mar 5, 2026
85.7Win Rate
5
Mar 4, 2026