Multi-Agent Reinforcement Learning on Multi-Agent MuJoCo HalfCheetah fore thigh
8,347Average ScoreMAT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MAT#examples=10%, pre-training status=Pre-trained2022.05 | 8,347 | 81 | |
| MAT#examples=5%, pre-training status=Pre-trained2022.05 | 7,952 | 109 | |
| MAT#examples=1%, pre-training status=Pre-trained2022.05 | 6,448 | 417 | |
| MAT#examples=0%, pre-training status=Pre-trained2022.05 | 5,631 | 321 | |
| MAPPO#examples=10%2022.05 | 3,519 | 59 | |
| MAPPO#examples=5%2022.05 | 3,340 | 52 | |
| MAPPO#examples=1%2022.05 | 3,171 | 83 | |
| MAPPO#examples=0%2022.05 | 3,087 | 110 | |
| MAT-from scratch#examples=10%, pre-training status=From scratch2022.05 | 2,600 | 215 | |
| MAT-from scratch#examples=5%, pre-training status=From scratch2022.05 | 1,021 | 177 | |
| MAT-from scratch#examples=1%, pre-training status=From scratch2022.05 | 0.82 | 14 | |
| MAT-from scratch#examples=0%, pre-training status=From scratch2022.05 | -0.29 | 0.3 |