Offline Reinforcement Learning on 1T10S Walker2D (Medium-Replay)
71.67Performance ScoreDFDT
Evaluation Results
| Method | Links | |
|---|---|---|
| DFDTDistribution Shift=BodyMass2024.10 | 71.67 | |
| DFDTDistribution Shift=JointNoise2024.10 | 71.236 | |
| IGDFDistribution Shift=JointNoise2024.10 | 66.834 | |
| IGDFDistribution Shift=BodyMass2024.10 | 62.494 | |
| D-CQLDistribution Shift=BodyMass2024.10 | 57.432 | |
| H2ODistribution Shift=BodyMass2024.10 | 56.11 | |
| H2ODistribution Shift=JointNoise2024.10 | 55.228 | |
| CQLDistribution Shift=BodyMass2024.10 | 54.753 | |
| D-CQLDistribution Shift=JointNoise2024.10 | 51.742 | |
| D-BCQDistribution Shift=BodyMass2024.10 | 51.447 | |
| BCQDistribution Shift=BodyMass2024.10 | 50.714 | |
| D-BCQDistribution Shift=JointNoise2024.10 | 50.714 | |
| BCQDistribution Shift=JointNoise2024.10 | 50.601 | |
| CQLDistribution Shift=JointNoise2024.10 | 50.6 | |
| AWRDistribution Shift=BodyMass2024.10 | 47.033 | |
| D-AWRDistribution Shift=JointNoise2024.10 | 36.807 | |
| D-AWRDistribution Shift=BodyMass2024.10 | 32.008 | |
| AWRDistribution Shift=JointNoise2024.10 | 31.623 | |
| D-MOPODistribution Shift=JointNoise2024.10 | 15.389 | |
| D-MOPODistribution Shift=BodyMass2024.10 | 12.129 | |
| MOPODistribution Shift=BodyMass2024.10 | 11.563 | |
| MOPODistribution Shift=JointNoise2024.10 | 11.379 | |
| D-BEARDistribution Shift=BodyMass2024.10 | 1.078 | |
| BEARDistribution Shift=JointNoise2024.10 | 0.474 | |
| D-BEARDistribution Shift=JointNoise2024.10 | 0.384 | |
| BEARDistribution Shift=BodyMass2024.10 | 0.067 |