Multi-Agent Reinforcement Learning on Google Football Research 3v1_k
92.19Winning RateATD-MAPPO
Evaluation results
| Method | Links | |
|---|---|---|
| ATD-MAPPOTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 92.19 | |
| MAPPOTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 90.12 | |
| OW-QMIXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 3.71 | |
| QPLEXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 2.05 | |
| MACPFTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.73 | |
| QMIXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.25 |