Offline Reinforcement Learning on Android Pen v2 (Human)
108.43Normalized ScorePPL
Evaluation Results
| Method | Links | |
|---|---|---|
| PPLevaluations=final 10, random seeds=52024.10 | 108.43 | |
| ReBRACevaluations=final 10, random seeds=52024.10 | 103.5 | |
| TD3+BCevaluations=final 10, random seeds=52024.10 | 81.8 | |
| IQLevaluations=final 10, random seeds=52024.10 | 81.5 | |
| OTR+IQLevaluations=final 10, random seeds=52024.10 | 66.82 | |
| CQLevaluations=final 10, random seeds=52024.10 | 37.5 | |
| BCevaluations=final 10, random seeds=52024.10 | 34.4 |