Continuous Control on OpenAI Gym MuJoCo Walker POMDP (test)
3,722.2Average ReturnDiff-SR
Evaluation Results
| Method | Links | |
|---|---|---|
| Diff-SRObservation Type=Full2024.06 | 3,722.2 | |
| Diff-SRObservation Type=Partial2024.06 | 1,860.5 | |
| Dreamer-v2Observation Type=Partial2024.06 | 1,305.8 | |
| µLV-RepObservation Type=Partial2024.06 | 1,298.1 | |
| PSRObservation Type=Partial2024.06 | 862.4 | |
| SAC-MLPObservation Type=Partial2024.06 | 736.5 | |
| SLACObservation Type=Partial2024.06 | 536.5 | |
| PolyGRADObservation Type=Partial2024.06 | 211.4 |