Offline Reinforcement Learning on Hopper expert
112.8Normalized ScoreAnti-exploration Method
Evaluation results
| Method | Links | |
|---|---|---|
| Anti-exploration Method2026.02 | 112.8 | |
| DMG2026.02 | 111.5 | |
| SAC-RND2026.02 | 109.7 | |
| GPC-SAC2026.02 | 109.5 | |
| IQL2026.02 | 109.4 | |
| CQL2026.02 | 96.5 | |
| DVDF-OTDF2025.12 | 48.9 | |
| DVDF-IGDF2025.12 | 44.6 | |
| OTDF2025.12 | 43.3 | |
| IGDF2025.12 | 29.6 | |
| IQL2025.12 | 28.3 | |
| QDFM2026.02 | 15 | |
| DARA2025.12 | 13 | |
| BOSA2025.12 | 7.3 | |
| BCQ2026.02 | 4.95 | |
| AWBC2026.02 | 1.03 | |
| AWAC2026.02 | 0.95 | |
| CQL2026.02 | 0.9 | |
| GreedyQ2026.02 | 0.9 |