Multi-Agent Reinforcement Learning on Google Football Research rpsk
84.82Winning RateATD-MAPPO
Evaluation results
| Method | Links | |
|---|---|---|
| ATD-MAPPOTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 84.82 | |
| MAPPOTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 78.46 | |
| OW-QMIXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 2.34 | |
| MACPFTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.1 | |
| QMIXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.08 | |
| QPLEXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.02 |