Meta-Reinforcement Learning on Walker Param-Sparse
82Average ReturnMetaSTAR
Evaluation results
| Method | Links | |
|---|---|---|
| MetaSTARMeta-testing Setting=Online2026.05 | 82 | |
| MetaSTARMeta-testing Setting=Offline2026.05 | 81 | |
| CORROMeta-testing Setting=Offline2026.05 | 78 | |
| CORROMeta-testing Setting=Online2026.05 | 76 | |
| FOCALMeta-testing Setting=Offline2026.05 | 76 | |
| FOCALMeta-testing Setting=Online2026.05 | 76 | |
| CSROMeta-testing Setting=Offline2026.05 | 75 | |
| CSROMeta-testing Setting=Online2026.05 | 75 | |
| UNICORNMeta-testing Setting=Offline2026.05 | 75 | |
| UNICORNMeta-testing Setting=Online2026.05 | 74 |