Meta-Reinforcement Learning on Point-Robot Sparse
42Average ReturnMetaSTAR
Evaluation results
| Method | Links | |
|---|---|---|
| MetaSTARMeta-testing Setting=Offline2026.05 | 42 | |
| UNICORNMeta-testing Setting=Offline2026.05 | 40 | |
| CORROMeta-testing Setting=Offline2026.05 | 38 | |
| FOCALMeta-testing Setting=Offline2026.05 | 28 | |
| MetaSTARMeta-testing Setting=Online2026.05 | 21 | |
| CSROMeta-testing Setting=Offline2026.05 | 13 | |
| CORROMeta-testing Setting=Online2026.05 | 10 | |
| UNICORNMeta-testing Setting=Online2026.05 | 6 | |
| FOCALMeta-testing Setting=Online2026.05 | 5 | |
| CSROMeta-testing Setting=Online2026.05 | 4 |