Payoff Evaluation on Continuous-action donation game Action vs L6, indirect-only matching (test)
3.06Per-interaction PayoffReciprocity Gradient
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Reciprocity GradientTrained Policy=π⁰, Matching=Indirect-only, Nplay=152026.05 | 3.06 | 68 | |
| DPGTrained Policy=π⁰, Matching=Indirect-only, Nplay=152026.05 | 1.9 | 42 | |
| TD3Trained Policy=π⁰, Matching=Indirect-only, Nplay=152026.05 | 1.39 | 31 | |
| DDPGTrained Policy=π⁰, Matching=Indirect-only, Nplay=152026.05 | 1.35 | 30 |