Multi-Agent Reinforcement Learning on Google Football Research psk
94.71Winning RateMAPPO
Evaluation results
| Method | Links | |
|---|---|---|
| MAPPOTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 94.71 | |
| ATD-MAPPOTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 93.12 | |
| OW-QMIXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 44.57 | |
| QPLEXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 17.07 | |
| QMIXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 16.41 | |
| MACPFTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.01 |