Offline Reinforcement Learning on D4RL AntMaze-Umaze v0
100Average Normalized ScoreDecision Mamba
Evaluation Results
| Method | Links | |
|---|---|---|
| Decision Mamba2024.06 | 100 | |
| LaMo2024.06 | 80 | |
| TD3+BCEvaluations=final 10, Seeds=5, State feature normalization=false2021.06 | 78.6 | |
| BC2024.06 | 63 | |
| DT2024.06 | 63 |