Multi-Agent Reinforcement Learning on Multi-Agent MuJoCo HalfCheetah fore foot
6,054Average Evaluation ScoreMAT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MAT#examples=10%, pre-training status=Pre-trained2022.05 | 6,054 | 172 | |
| MAT#examples=5%, pre-training status=Pre-trained2022.05 | 4,856 | 146 | |
| MAT-from scratch#examples=10%, pre-training status=From scratch2022.05 | 2,877 | 106 | |
| MAPPO#examples=10%2022.05 | 2,480 | 239 | |
| MAPPO#examples=5%2022.05 | 2,025 | 371 | |
| MAT#examples=1%, pre-training status=Pre-trained2022.05 | 1,955 | 232 | |
| MAT-from scratch#examples=5%, pre-training status=From scratch2022.05 | 1,821 | 157 | |
| MAT#examples=0%, pre-training status=Pre-trained2022.05 | 1,313 | 512 | |
| MAPPO#examples=1%2022.05 | 970 | 185 | |
| MAPPO#examples=0%2022.05 | 623 | 44 | |
| MAT-from scratch#examples=0%, pre-training status=From scratch2022.05 | -0.37 | 0.2 | |
| MAT-from scratch#examples=1%, pre-training status=From scratch2022.05 | -2.25 | 7.9 |