Multi-Agent Reinforcement Learning on Multi-Agent MuJoCo HalfCheetah fore shin
4,373Average Evaluation ScoreMAT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MAT#examples=10%, pre-training status=Pre-trained2022.05 | 4,373 | 83 | |
| MAT#examples=5%, pre-training status=Pre-trained2022.05 | 3,851 | 57 | |
| MAPPO#examples=10%2022.05 | 3,310 | 54 | |
| MAPPO#examples=5%2022.05 | 3,096 | 59 | |
| MAT-from scratch#examples=10%, pre-training status=From scratch2022.05 | 3,003 | 316 | |
| MAT#examples=1%, pre-training status=Pre-trained2022.05 | 2,617 | 71 | |
| MAPPO#examples=1%2022.05 | 2,457 | 125 | |
| MAT#examples=0%, pre-training status=Pre-trained2022.05 | 2,435 | 13 | |
| MAPPO#examples=0%2022.05 | 1,715 | 55 | |
| MAT-from scratch#examples=5%, pre-training status=From scratch2022.05 | 1,461 | 101 | |
| MAT-from scratch#examples=0%, pre-training status=From scratch2022.05 | -0.15 | 0.06 | |
| MAT-from scratch#examples=1%, pre-training status=From scratch2022.05 | -0.96 | 6 |