Offline Reinforcement Learning on Android Hammer v2 (Human)
133.8ScoreReBRAC
Evaluation Results
| Method | Links | |
|---|---|---|
| ReBRACevaluations=final 10, random seeds=52024.10 | 133.8 | |
| PPLevaluations=final 10, random seeds=52024.10 | 130.2 | |
| BCevaluations=final 10, random seeds=52024.10 | 125.6 | |
| TD3+BCevaluations=final 10, random seeds=52024.10 | 117 | |
| IQLevaluations=final 10, random seeds=52024.10 | 106.5 | |
| CQLevaluations=final 10, random seeds=52024.10 | 86.7 | |
| CQLevaluations=final 10, random seeds=52024.10 | 4.4 | |
| IQLevaluations=final 10, random seeds=52024.10 | 2.5 | |
| PPLevaluations=final 10, random seeds=52024.10 | 2 | |
| OTR+IQLevaluations=final 10, random seeds=52024.10 | 1.79 | |
| BCevaluations=final 10, random seeds=52024.10 | 1.5 | |
| TD3+BCevaluations=final 10, random seeds=52024.10 | 0.4 | |
| ReBRACevaluations=final 10, random seeds=52024.10 | 0.2 |