Meta-Reinforcement Learning on Ant Dir
236Average ReturnMetaSTAR
Evaluation results
| Method | Links | |
|---|---|---|
| MetaSTARMeta-testing Setting=Offline2026.05 | 236 | |
| MetaSTARMeta-testing Setting=Online2026.05 | 230 | |
| UNICORNMeta-testing Setting=Offline2026.05 | 210 | |
| FOCALMeta-testing Setting=Offline2026.05 | 194 | |
| CORROMeta-testing Setting=Offline2026.05 | 183 | |
| CORROMeta-testing Setting=Online2026.05 | 149 | |
| CSROMeta-testing Setting=Offline2026.05 | 141 | |
| UNICORNMeta-testing Setting=Online2026.05 | 140 | |
| FOCALMeta-testing Setting=Online2026.05 | 115 | |
| CSROMeta-testing Setting=Online2026.05 | 109 |