Offline Reinforcement Learning on D4RL Ant Medium-Expert v2
136.2Normalized ScoreDecision Mamba
Evaluation Results
| Method | Links | |
|---|---|---|
| Decision Mamba2024.06 | 136.2 | |
| LaMo2024.06 | 134.8 | |
| DT2024.06 | 129.6 | |
| BC2024.06 | 99.8 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Decision Mamba2024.06 | 136.2 | |
| LaMo2024.06 | 134.8 | |
| DT2024.06 | 129.6 | |
| BC2024.06 | 99.8 |