Offline Reinforcement Learning on Android Pen v2 (Cloned)
113.97Normalized ScorePPL
Evaluation Results
| Method | Links | |
|---|---|---|
| PPLevaluations=final 10, random seeds=52024.10 | 113.97 | |
| ReBRACevaluations=final 10, random seeds=52024.10 | 91.8 | |
| OTR+IQLevaluations=final 10, random seeds=52024.10 | 78.7 | |
| TD3+BCevaluations=final 10, random seeds=52024.10 | 61.4 | |
| BCevaluations=final 10, random seeds=52024.10 | 56.9 | |
| IQLevaluations=final 10, random seeds=52024.10 | 46.8 | |
| CQLevaluations=final 10, random seeds=52024.10 | 39.2 |