Joint action and signal payoff optimization on ProudCoop+AllD (off-diagonal)
2.39Payoff (Per Interaction)DDPG
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DDPGTouter=15, Seeds=32026.05 | 2.39 | 106 | |
| TD3Touter=15, Seeds=32026.05 | 2.37 | 105 | |
| Reciprocity Gradient2026.05 | 2.34 | 104 | |
| DPGTouter=15, Seeds=32026.05 | 1.88 | 83 |