Meta-Reinforcement Learning on Cheetah-Vel
60Average ReturnCORRO
Evaluation results
| Method | Links | |
|---|---|---|
| CORROMeta-testing Setting=Online2026.05 | 60 | |
| MetaSTARMeta-testing Setting=Online2026.05 | 60 | |
| CSROMeta-testing Setting=Online2026.05 | 57 | |
| FOCALMeta-testing Setting=Online2026.05 | 57 | |
| UNICORNMeta-testing Setting=Online2026.05 | 56 | |
| CSROMeta-testing Setting=Offline2026.05 | 38 | |
| FOCALMeta-testing Setting=Offline2026.05 | 36 | |
| CORROMeta-testing Setting=Offline2026.05 | 34 | |
| MetaSTARMeta-testing Setting=Offline2026.05 | 33 | |
| UNICORNMeta-testing Setting=Offline2026.05 | 32 |