Multi-Agent Reinforcement Learning on Multi-Agent MuJoCo HalfCheetah back foot
5,646Average ScoreMAT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MAT#examples=10%, pre-training status=Pre-trained2022.05 | 5,646 | 79 | |
| MAT#examples=5%, pre-training status=Pre-trained2022.05 | 4,691 | 235 | |
| MAPPO#examples=10%2022.05 | 3,304 | 129 | |
| MAPPO#examples=5%2022.05 | 3,221 | 119 | |
| MAPPO#examples=1%2022.05 | 3,017 | 135 | |
| MAPPO#examples=0%2022.05 | 2,936 | 301 | |
| MAT#examples=1%, pre-training status=Pre-trained2022.05 | 2,837 | 95 | |
| MAT#examples=0%, pre-training status=Pre-trained2022.05 | 2,100 | 89 | |
| MAT-from scratch#examples=10%, pre-training status=From scratch2022.05 | 1,635 | 1,184 | |
| MAT-from scratch#examples=5%, pre-training status=From scratch2022.05 | 670 | 1,098 | |
| MAT-from scratch#examples=0%, pre-training status=From scratch2022.05 | -0.44 | 0.4 | |
| MAT-from scratch#examples=1%, pre-training status=From scratch2022.05 | -5.18 | 11 |