Offline Reinforcement Learning on HalfCheetah medium-expert
107.6Normalized ScoreSAC-RND
Evaluation results
| Method | Links | |
|---|---|---|
| SAC-RND2026.02 | 107.6 | |
| Anti-exploration Method2026.02 | 104.9 | |
| Q-ALIGN DT2026.05 | 98.8 | |
| QT2026.05 | 96.1 | |
| DM2026.05 | 93.9 | |
| CGDT2026.05 | 93.6 | |
| QCS2026.05 | 93.3 | |
| O-DICE2026.02 | 93.2 | |
| LSDT2026.05 | 93.2 | |
| RADT2026.05 | 93.1 | |
| DC2026.05 | 93 | |
| DMG2026.02 | 91.1 | |
| TD3+BC2026.05 | 90.7 | |
| GPC-SAC2026.02 | 87.1 | |
| DT2026.05 | 86.8 | |
| IQL2026.02 | 86.7 | |
| IQL2026.05 | 86.7 | |
| TD3-CVAE2026.02 | 86.1 | |
| CQL2026.02 | 75.6 | |
| DVDF-IGDF2025.12 | 21.9 | |
| DVDF-OTDF2025.12 | 19.8 | |
| BOSA2025.12 | 15.4 | |
| IGDF2025.12 | 14.9 | |
| DARA2025.12 | 13.7 | |
| IQL2025.12 | 12.3 | |
| OTDF2025.12 | 11.5 |