Policy Optimization on Pandemic
3.65True PerformanceLinear Max-Min
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Linear Max-MinEnvironment=Pandemic2026.04 | 3.65 | 7.6 | -682,000 | 0.65 | -0.17 | |
| Linear Max-Min2026.04 | 3.65 | 7.6 | -682,000 | 0.65 | -0.17 | |
| Max-MinEnvironment=Pandemic2026.04 | 1.25 | 1.25 | -63.29 | -1.11 | -1.11 | |
| Max-Min2026.04 | 1.25 | 1.25 | -63.29 | -1.11 | -1.11 | |
| ORPO*Environment=Pandemic2026.04 | 1.18 | 1.18 | -4,460,000 | -1.36 | -1.36 | |
| ORPO*2026.04 | 1.18 | 1.18 | -4,460,000 | -1.36 | -1.36 | |
| ORPOEnvironment=Pandemic2026.04 | -1.04 | 1.75 | -5,310,000 | -2.41 | -2.65 | |
| ORPO2026.04 | -1.04 | 1.75 | -5,310,000 | -2.41 | -2.65 |