Signal-component payoff optimization on ProudCoop+AllD discriminative cell c=5
1.2Payoff (Per Interaction)Reciprocity Gradient
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Reciprocity GradientTouter=125, Seeds=52026.05 | 1.2 | 96 | |
| DPGTouter=125, Seeds=102026.05 | 0.76 | 61 | |
| TD3Touter=125, Seeds=102026.05 | 0.74 | 59 | |
| DDPGTouter=125, Seeds=102026.05 | 0.66 | 53 |