Reward Hacking Analysis on Reward Hacking Evaluation Environment
148.84V^piEO
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| EOCondition=EO2026.04 | 148.84 | 100 | 64.5 | 70.8 | 64.5 | |
| MOCondition=MO2026.04 | 77.95 | 52.4 | 60.6 | 58 | 31.7 | |
| SmartTutorCondition=ST2026.04 | 64.42 | 43.3 | 23.7 | 5.8 | 10.2 | |
| MASCondition=MAS2026.04 | 47.52 | 31.9 | 32.8 | 39.1 | 10.5 |