Value function estimation on Game B matrix (train)
10Estimated PayoffQMIX
Evaluation results
| Method | Links | |
|---|---|---|
| QMIXAction u1=C, Action u2=C, Strategy=ϵ-greedy, Variant=standard2025.11 | 10 | |
| QMIXAction u1=C, Action u2=A, Strategy=ϵ-greedy, Variant=standard2025.11 | 5.6 | |
| QMIXAction u1=C, Action u2=B, Strategy=ϵ-greedy, Variant=standard2025.11 | 5.6 | |
| QMIXAction u1=A, Action u2=C, Strategy=ϵ-greedy, Variant=standard2025.11 | 4.1 | |
| QMIXAction u1=B, Action u2=C, Strategy=ϵ-greedy, Variant=standard2025.11 | 4.1 | |
| QMIXAction u1=A, Action u2=A, Strategy=ϵ-greedy, Variant=standard2025.11 | 0.1 | |
| QMIXAction u1=A, Action u2=B, Strategy=ϵ-greedy, Variant=standard2025.11 | 0.1 | |
| QMIXAction u1=B, Action u2=A, Strategy=ϵ-greedy, Variant=standard2025.11 | 0.1 | |
| QMIXAction u1=B, Action u2=B, Strategy=ϵ-greedy, Variant=standard2025.11 | 0.1 |