List your company
ResearchFormerly WizWand

Meta-Reinforcement Learning on Cheetah-Vel-Sparse (OOD)

296Average ReturnMetaSTAR
6.8881.94157232.06May 30, 2026
Updated 5mo ago

Evaluation results

MethodLinks
MetaSTARMeta-testing Setting=Offline2026.05296
CORROMeta-testing Setting=Offline2026.05260
MetaSTARMeta-testing Setting=Online2026.05260
FOCALMeta-testing Setting=Offline2026.05242
UNICORNMeta-testing Setting=Offline2026.05238
CORROMeta-testing Setting=Online2026.05216
UNICORNMeta-testing Setting=Online2026.05212
FOCALMeta-testing Setting=Online2026.05196
CSROMeta-testing Setting=Offline2026.05169
MetaSTAREpisode=Final2026.05142
CSROMeta-testing Setting=Online2026.05137
UNICORNEpisode=Final2026.05135
FOCALEpisode=Final2026.05119
CSROEpisode=Final2026.0596
CORROEpisode=Final2026.0518