Regret Analysis on Bargaining Game 1000 trajectories, pi^U behavior policy
2.12RegretCOffeE-PSRO, R2D
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| COffeE-PSRO, R2DAlg=COffeE-PSRO, Mexpl=R2D, Meval=R2D2026.02 | 2.12 | 0.27 | — | |
| COffeE-PSRO, R2DAlg=COffeE-PSRO, Mexpl=R2D, Meval=RD2026.02 | 2.4 | 0.55 | — | |
| OEF-BC, R2DAlg=OEF-BC, Mexpl=R2D, Meval=RD2026.02 | 2.62 | 0.22 | 0.13 | |
| COffeE-PSRO, RDAlg=COffeE-PSRO, Mexpl=RD, Meval=RD2026.02 | 2.64 | 0.55 | 0.17 | |
| OEF-BC, R2DAlg=OEF-BC, Mexpl=R2D, Meval=R2D2026.02 | 2.7 | 0.39 | 0.01 | |
| COffeE-PSRO, RDAlg=COffeE-PSRO, Mexpl=RD, Meval=R2D2026.02 | 2.85 | 0.91 | 0.02 | |
| OEF-BC, RDAlg=OEF-BC, Mexpl=RD, Meval=R2D2026.02 | 2.92 | 0.75 | 0.01 | |
| OEF-BC, RDAlg=OEF-BC, Mexpl=RD, Meval=RD2026.02 | 2.96 | 1.07 | 0.08 | |
| OEF, R2DAlg=OEF, Mexpl=R2D, Meval=RD2026.02 | 3.2 | 0.37 | 0.01 | |
| OEF, R2DAlg=OEF, Mexpl=R2D, Meval=R2D2026.02 | 3.25 | 1 | 0.35 | |
| OEF, RDAlg=OEF, Mexpl=RD, Meval=R2D2026.02 | 3.68 | 1.63 | 0.01 | |
| OEF, RDAlg=OEF, Mexpl=RD, Meval=RD2026.02 | 3.74 | 2.1 | 0.04 |