Offline Reinforcement Learning on Android Pen v2 (Expert)
1.541Normalized ScoreReBRAC
Evaluation Results
| Method | Links | |
|---|---|---|
| ReBRACevaluations=final 10, random seeds=52024.10 | 1.541 | |
| PPLevaluations=final 10, random seeds=52024.10 | 1.5233 | |
| TD3+BCevaluations=final 10, random seeds=52024.10 | 1.46 | |
| IQLevaluations=final 10, random seeds=52024.10 | 1.336 | |
| CQLevaluations=final 10, random seeds=52024.10 | 1.07 | |
| BCevaluations=final 10, random seeds=52024.10 | 0.851 |