Continuous Control on OpenAI Gym MuJoCo Humanoid POMDP (test)
823.1Average ReturnDiff-SR
Evaluation Results
| Method | Links | |
|---|---|---|
| Diff-SRObservation Type=Full2024.06 | 823.1 | |
| µLV-RepObservation Type=Partial2024.06 | 806.7 | |
| PolyGRADObservation Type=Partial2024.06 | 764.5 | |
| Dreamer-v2Observation Type=Partial2024.06 | 672.5 | |
| Diff-SRObservation Type=Partial2024.06 | 650.1 | |
| PSRObservation Type=Partial2024.06 | 534.4 | |
| SLACObservation Type=Partial2024.06 | 387.4 | |
| SAC-MLPObservation Type=Partial2024.06 | 242.1 |