Multi-Agent Reinforcement Learning on Multi-Agent MuJoCo HalfCheetah back thigh
7,460Avg ScoreMAT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MAT#examples=10%, pre-training status=Pre-trained2022.05 | 7,460 | 61 | |
| MAT#examples=5%, pre-training status=Pre-trained2022.05 | 7,101 | 119 | |
| MAT#examples=1%, pre-training status=Pre-trained2022.05 | 5,641 | 150 | |
| MAT#examples=0%, pre-training status=Pre-trained2022.05 | 5,361 | 45 | |
| MAPPO#examples=10%2022.05 | 3,353 | 71 | |
| MAPPO#examples=5%2022.05 | 3,217 | 33 | |
| MAPPO#examples=1%2022.05 | 3,060 | 143 | |
| MAPPO#examples=0%2022.05 | 3,043 | 79 | |
| MAT-from scratch#examples=10%, pre-training status=From scratch2022.05 | 2,067 | 861 | |
| MAT-from scratch#examples=5%, pre-training status=From scratch2022.05 | 930 | 589 | |
| MAT-from scratch#examples=0%, pre-training status=From scratch2022.05 | -0.54 | 0.3 | |
| MAT-from scratch#examples=1%, pre-training status=From scratch2022.05 | -4.87 | 7.7 |