Joint action and signal payoff optimization on HybridCoop+AllD Headline discriminative cell
2.225Per-interaction PayoffReciprocity Gradient
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Reciprocity GradientTouter=200, Seeds=202026.05 | 2.225 | 99 | 20 | |
| DPGTouter=125, Seeds=102026.05 | 1.81 | 80 | — | |
| DDPGTouter=125, Seeds=102026.05 | 1.55 | 69 | — | |
| TD3Touter=125, Seeds=102026.05 | 1.54 | 69 | — |