Policy Optimization under Non-Exponential Discounting on Time-varying Hyperbolic Discounting Case 3
0.0074Global L1 ErrorPG-DPO
Evaluation Results
| Method | Links | |
|---|---|---|
| PG-DPO2026.05 | 0.0074 | |
| DPO2026.05 | 0.131 | |
| PINN2026.05 | 0.267 | |
| PPO2026.05 | 0.289 | |
| Deep BSVIE2026.05 | 1.02 |