Offline Reinforcement Learning on Walker Medium Gym-MuJoCo D4RL
84.7Normalized ScoreTT(+Q)
Evaluation results
| Method | Links | |
|---|---|---|
| TT(+Q)Configuration=Trifle2023.10 | 84.7 | |
| TD3(+BC)2023.10 | 83.7 | |
| TTConfiguration=Trifle2023.10 | 83.1 | |
| Decision Diffuser2024.06 | 82.5 | |
| DD2023.10 | 82.5 | |
| TT(+Q)Configuration=base2023.10 | 82.2 | |
| DTConfiguration=Trifle2023.10 | 81.3 | |
| Decision Mamba2024.06 | 80.3 | |
| Diffuser2024.06 | 79.7 | |
| Critic-Guided Decision Transformer2024.06 | 79.1 | |
| Trajectory Transformer2024.06 | 79 | |
| TTConfiguration=base2023.10 | 79 | |
| IQL2023.10 | 78.3 | |
| %BC2023.10 | 75 | |
| DTConfiguration=base2023.10 | 74 | |
| CQL2023.10 | 72.5 |