Offline Reinforcement Learning on D4RL Mujoco Halfcheetah-Medium-Expert v2
94.3Normalized ScoreTAILO
Evaluation results
| Method | Links | |
|---|---|---|
| TAILO2023.11 | 94.3 | |
| TSRLRatio=1, Size=2M2023.06 | 92 | |
| CQLRatio=1, Size=2M2023.06 | 91.6 | |
| TD3+BCRatio=1, Size=2M2023.06 | 90.7 | |
| IQLRatio=1, Size=2M2023.06 | 86.7 | |
| DOGERatio=1, Size=2M2023.06 | 78.7 | |
| MOPO2023.11 | 63.3 | |
| MOPORatio=1, Size=2M2023.06 | 63.3 | |
| BCRatio=1, Size=2M2023.06 | 55.2 | |
| MOReL2023.11 | 53.3 | |
| TSRLRatio=1/200, Size=10k2023.06 | 39.9 | |
| DOGERatio=1/200, Size=10k2023.06 | 26.7 | |
| CQLRatio=1/200, Size=10k2023.06 | 26.5 | |
| BCRatio=1/200, Size=10k2023.06 | 19.1 | |
| IQLRatio=1/200, Size=10k2023.06 | 16.5 | |
| TD3+BCRatio=1/200, Size=10k2023.06 | 15.4 | |
| MOPORatio=1/200, Size=10k2023.06 | -1.1 |