Joint action and signal payoff optimization on L6 warmup (off-diagonal)
3.65Payoff (Per Interaction)Reciprocity Gradient
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Reciprocity Gradient2026.05 | 3.65 | 81 | |
| DDPGTouter=15, Seeds=32026.05 | 1.16 | 26 | |
| DPGTouter=15, Seeds=32026.05 | 0.57 | 13 | |
| TD3Touter=15, Seeds=32026.05 | 0.32 | 7 |