Offline Reinforcement Learning on 1T10S Hopper (Medium-Expert)
111.587ScoreD-BCQ
Evaluation Results
| Method | Links | |
|---|---|---|
| D-BCQDistribution Shift=JointNoise2024.10 | 111.587 | |
| D-BCQDistribution Shift=BodyMass2024.10 | 110.014 | |
| H2ODistribution Shift=JointNoise2024.10 | 109.457 | |
| BCQDistribution Shift=BodyMass2024.10 | 109.367 | |
| H2ODistribution Shift=BodyMass2024.10 | 108.872 | |
| BCQDistribution Shift=JointNoise2024.10 | 108.639 | |
| IGDFDistribution Shift=BodyMass2024.10 | 105.465 | |
| IGDFDistribution Shift=JointNoise2024.10 | 99.057 | |
| D-CQLDistribution Shift=JointNoise2024.10 | 94.128 | |
| D-AWRDistribution Shift=BodyMass2024.10 | 78.262 | |
| AWRDistribution Shift=JointNoise2024.10 | 74.708 | |
| DFDTDistribution Shift=JointNoise2024.10 | 74.306 | |
| CQLDistribution Shift=JointNoise2024.10 | 72.512 | |
| D-CQLDistribution Shift=BodyMass2024.10 | 72.149 | |
| DFDTDistribution Shift=BodyMass2024.10 | 70.703 | |
| CQLDistribution Shift=BodyMass2024.10 | 70.467 | |
| D-AWRDistribution Shift=JointNoise2024.10 | 60.952 | |
| AWRDistribution Shift=BodyMass2024.10 | 57.595 | |
| BEARDistribution Shift=JointNoise2024.10 | 39.031 | |
| D-BEARDistribution Shift=JointNoise2024.10 | 33.052 | |
| D-MOPODistribution Shift=JointNoise2024.10 | 32.589 | |
| D-BEARDistribution Shift=BodyMass2024.10 | 31.09 | |
| MOPODistribution Shift=BodyMass2024.10 | 30.541 | |
| D-MOPODistribution Shift=BodyMass2024.10 | 30.54 | |
| MOPODistribution Shift=JointNoise2024.10 | 30.537 | |
| BEARDistribution Shift=BodyMass2024.10 | 22.934 |