Multi-Agent Reinforcement Learning on SMAC Maps
595m_vs_6m Scoredmix-DA
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| dmix-DASight View=0, Integrated DAgger=IGM-DA2022.09 | 59 | 91.7 | 46.2 | 99.8 | 40.6 | 64.4 | 67 | — | — | — | |
| dmixSight View=02022.09 | 58.7 | 76.2 | 0 | 99.4 | 3.3 | 64.7 | 50.4 | — | — | — | |
| qmix-DASight View=0, Integrated DAgger=IGM-DA2022.09 | 50.6 | 93.3 | 55.4 | 99.2 | 43.9 | 70.8 | 68.9 | — | — | — | |
| qplex-DASight View=0, Integrated DAgger=IGM-DA2022.09 | 38.9 | 88.3 | 55.4 | 99.6 | 31.6 | 64.8 | 63.1 | — | — | — | |
| qmixSight View=02022.09 | 36.4 | 90.2 | 26.2 | 98.3 | 1.9 | 33.9 | 47.8 | — | — | — | |
| MAPPONumber of online examples=10%2022.05 | 21.9 | — | 36.2 | 100 | — | — | — | 26.8 | 100 | 97.5 | |
| MATNumber of online examples=10%2022.05 | 18.8 | — | 62.5 | 100 | — | — | — | 71.2 | 100 | 100 | |
| MATNumber of online examples=5%2022.05 | 5.8 | — | 33.8 | 100 | — | — | — | 53.8 | 100 | 82.5 | |
| qplexSight View=02022.09 | 5 | 87 | 0 | 98.7 | 18.9 | 36.2 | 41 | — | — | — | |
| MAPPONumber of online examples=5%2022.05 | 4.3 | — | 13.8 | 100 | — | — | — | 26.2 | 100 | 73.8 | |
| MAT-from scratchNumber of online examples=10%2022.05 | 3.8 | — | 0 | 92.5 | — | — | — | 0.3 | 96.3 | 87.5 | |
| MAT-from scratchNumber of online examples=5%2022.05 | 1.9 | — | 0 | 10.6 | — | — | — | 0 | 19.3 | 7.5 | |
| MATNumber of online examples=0%2022.05 | 0 | — | 0 | 100 | — | — | — | 0 | 0 | 3.1 | |
| MATNumber of online examples=1%2022.05 | 0 | — | 0 | 100 | — | — | — | 6.3 | 15.6 | 5.6 | |
| MAPPONumber of online examples=0%2022.05 | 0 | — | 0 | 100 | — | — | — | 9.4 | 0 | 0 | |
| MAPPONumber of online examples=1%2022.05 | 0 | — | 0 | 100 | — | — | — | 15 | 43.1 | 4.3 | |
| MAT-from scratchNumber of online examples=0%2022.05 | 0 | — | 0 | 0 | — | — | — | 0 | 0 | 0 | |
| MAT-from scratchNumber of online examples=1%2022.05 | 0 | — | 0 | 0 | — | — | — | 0 | 0 | 0 |