Offline Reinforcement Learning on Walker Gym-MuJoCo Medium-Expert D4RL
111.6Normalized ScoreDecision Mamba
Evaluation results
| Method | Links | |
|---|---|---|
| Decision Mamba2024.06 | 111.6 | |
| TD3(+BC)2023.10 | 110.1 | |
| TT(+Q)Configuration=Trifle2023.10 | 109.6 | |
| IQL2023.10 | 109.6 | |
| Critic-Guided Decision Transformer2024.06 | 109.3 | |
| TTConfiguration=Trifle2023.10 | 109.3 | |
| TT(+Q)Configuration=base2023.10 | 109.3 | |
| %BC2023.10 | 109 | |
| Decision Diffuser2024.06 | 108.8 | |
| DD2023.10 | 108.8 | |
| CQL2023.10 | 108.8 | |
| DTConfiguration=Trifle2023.10 | 108.6 | |
| Diffuser2024.06 | 108.4 | |
| DTConfiguration=base2023.10 | 108.1 | |
| TrifleConstraint=Action-Space-Constrained (A=0.5)2023.10 | 105.1 | |
| TTConstraint=Action-Space-Constrained (A=0.5)2023.10 | 103.6 | |
| Trajectory Transformer2024.06 | 101.9 | |
| TTConfiguration=base2023.10 | 101.9 |