Meta-Reinforcement Learning on Walker-Param
140Average ReturnMetaSTAR
Evaluation results
| Method | Links | |
|---|---|---|
| MetaSTARMeta-testing Setting=Offline2026.05 | 140 | |
| MetaSTARMeta-testing Setting=Online2026.05 | 139 | |
| CORROMeta-testing Setting=Online2026.05 | 127 | |
| CORROMeta-testing Setting=Offline2026.05 | 126 | |
| UNICORNMeta-testing Setting=Online2026.05 | 117 | |
| FOCALMeta-testing Setting=Offline2026.05 | 116 | |
| UNICORNMeta-testing Setting=Offline2026.05 | 103 | |
| FOCALMeta-testing Setting=Online2026.05 | 84 | |
| CSROMeta-testing Setting=Online2026.05 | 54 | |
| CSROMeta-testing Setting=Offline2026.05 | 28 |