Offline Reinforcement Learning on HalfCheetah Gym-MuJoCo Medium-Replay D4RL
48.9Normalized ScoreTT(+Q)
Evaluation Results
| Method | Links | |
|---|---|---|
| TT(+Q)Configuration=Trifle2023.10 | 48.9 | |
| TT(+Q)Configuration=base2023.10 | 48.2 | |
| CQL2023.10 | 45.5 | |
| TTConfiguration=Trifle2023.10 | 45 | |
| TD3(+BC)2023.10 | 44.6 | |
| IQL2023.10 | 44.2 | |
| Diffuser2024.06 | 42.2 | |
| Trajectory Transformer2024.06 | 41.9 | |
| TTConfiguration=base2023.10 | 41.9 | |
| Decision Mamba2024.06 | 40.8 | |
| %BC2023.10 | 40.6 | |
| Critic-Guided Decision Transformer2024.06 | 40.4 | |
| Decision Diffuser2024.06 | 39.3 | |
| DD2023.10 | 39.3 | |
| DTConfiguration=Trifle2023.10 | 39.2 | |
| DTConfiguration=base2023.10 | 36.6 |