Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-Agent Reinforcement Learning on Simple Spread N=6

0.0107Collisions

MAPPO

-0.1716721.0593392.290353.521361Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.06
0.01070.00072.82
2026.06
0.01740.00122.88
2026.06
0.01830.00127.23
2026.06
0.01880.00134.48
2026.06
0.02170.00141.85
2026.06
0.02430.00161.8
2026.06
0.0310.00217.37
2026.06
0.03130.00212.88
2026.06
0.08020.005312.87
2026.06
0.0960.006414.21
2026.06
0.10580.007115.83
2026.06
0.14250.009524.17
2026.06
0.14580.009724
2026.06
0.15440.010324.17
2026.06
1.20.087.33
2026.06
1.530.111.75
2026.06
1.720.1122.38
2026.06
2.890.1928.67
2026.06
2.990.233.21
2026.06
3.90.2634.83
2026.06
4.130.2833.29
2026.06
4.280.2933.92
2026.06
4.570.333.75