Multi-Agent Reinforcement Learning on Google Football Research ca_easy
0.9743Winning RateATD-MAPPO
Evaluation results
| Method | Links | |
|---|---|---|
| ATD-MAPPOTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.9743 | |
| MAPPOTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.8292 | |
| QMIXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.1249 | |
| OW-QMIXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.0952 | |
| QPLEXTime steps=50M, Evaluation processes=32, Seeds=102026.05 | 0.0151 | |
| MACPFTime steps=50M, Evaluation processes=32, Seeds=102026.05 | -0.0019 |