Multi-Agent Reinforcement Learning on Google Football Research corner
0.6079Winning RateATD-MAPPO
Evaluation results
| Method | Links | |
|---|---|---|
| ATD-MAPPOTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.6079 | |
| MAPPOTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.4919 | |
| QMIXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | -0.0605 | |
| QPLEXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | -0.0892 | |
| MACPFTime steps=50M, Evaluation processes=32, Seeds=102026.05 | -0.1221 | |
| OW-QMIXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | -0.1244 |