Offline Reinforcement Learning on 1T10S HalfCheetah (Medium-Expert)
89.22ScoreD-AWR
Evaluation Results
| Method | Links | |
|---|---|---|
| D-AWRDistribution Shift=JointNoise2024.10 | 89.22 | |
| D-AWRDistribution Shift=BodyMass2024.10 | 89.201 | |
| AWRDistribution Shift=JointNoise2024.10 | 88.647 | |
| AWRDistribution Shift=BodyMass2024.10 | 88.155 | |
| D-CQLDistribution Shift=JointNoise2024.10 | 84.21 | |
| CQLDistribution Shift=JointNoise2024.10 | 84.09 | |
| DFDTDistribution Shift=JointNoise2024.10 | 82.476 | |
| DFDTDistribution Shift=BodyMass2024.10 | 78.093 | |
| D-BCQDistribution Shift=JointNoise2024.10 | 71.007 | |
| D-BCQDistribution Shift=BodyMass2024.10 | 63.465 | |
| D-CQLDistribution Shift=BodyMass2024.10 | 62.665 | |
| BCQDistribution Shift=JointNoise2024.10 | 62.486 | |
| BCQDistribution Shift=BodyMass2024.10 | 61.771 | |
| CQLDistribution Shift=BodyMass2024.10 | 61.104 | |
| H2ODistribution Shift=JointNoise2024.10 | 60.23 | |
| D-MOPODistribution Shift=JointNoise2024.10 | 60.014 | |
| H2ODistribution Shift=BodyMass2024.10 | 58.192 | |
| D-MOPODistribution Shift=BodyMass2024.10 | 56.616 | |
| MOPODistribution Shift=JointNoise2024.10 | 54.63 | |
| MOPODistribution Shift=BodyMass2024.10 | 51.04 | |
| IGDFDistribution Shift=JointNoise2024.10 | 48.192 | |
| IGDFDistribution Shift=BodyMass2024.10 | 48.112 | |
| D-BEARDistribution Shift=JointNoise2024.10 | 8.789 | |
| BEARDistribution Shift=BodyMass2024.10 | 4.356 | |
| BEARDistribution Shift=JointNoise2024.10 | 3.195 | |
| D-BEARDistribution Shift=BodyMass2024.10 | 2.948 |