Offline Reinforcement Learning on Hopper 1T10S (Medium)
101.244ScoreH2O
Evaluation Results
| Method | Links | |
|---|---|---|
| H2ODistribution Shift=JointNoise2024.10 | 101.244 | |
| H2ODistribution Shift=BodyMass2024.10 | 100.754 | |
| IGDFDistribution Shift=JointNoise2024.10 | 78.467 | |
| IGDFDistribution Shift=BodyMass2024.10 | 75.326 | |
| D-BCQDistribution Shift=JointNoise2024.10 | 74.853 | |
| BCQDistribution Shift=JointNoise2024.10 | 74.559 | |
| CQLDistribution Shift=JointNoise2024.10 | 71.495 | |
| DFDTDistribution Shift=BodyMass2024.10 | 66.133 | |
| D-CQLDistribution Shift=JointNoise2024.10 | 63.611 | |
| D-AWRDistribution Shift=JointNoise2024.10 | 61.463 | |
| DFDTDistribution Shift=JointNoise2024.10 | 59.76 | |
| AWRDistribution Shift=JointNoise2024.10 | 57.021 | |
| CQLDistribution Shift=BodyMass2024.10 | 49.094 | |
| D-CQLDistribution Shift=BodyMass2024.10 | 45.101 | |
| D-AWRDistribution Shift=BodyMass2024.10 | 26.594 | |
| D-BCQDistribution Shift=BodyMass2024.10 | 26.487 | |
| AWRDistribution Shift=BodyMass2024.10 | 25.843 | |
| D-BEARDistribution Shift=BodyMass2024.10 | 25.608 | |
| D-MOPODistribution Shift=JointNoise2024.10 | 24.992 | |
| BCQDistribution Shift=BodyMass2024.10 | 24.853 | |
| MOPODistribution Shift=JointNoise2024.10 | 23.556 | |
| BEARDistribution Shift=BodyMass2024.10 | 22.436 | |
| D-MOPODistribution Shift=BodyMass2024.10 | 21.495 | |
| MOPODistribution Shift=BodyMass2024.10 | 20.765 | |
| D-BEARDistribution Shift=JointNoise2024.10 | 10.576 | |
| BEARDistribution Shift=JointNoise2024.10 | 8.536 |