ResearchBenchmarksMeta-Reinforcement Learning on MuJoCo HalfCheetah Velocity variation (test)Meta-Reinforcement Learning on MuJoCo HalfCheetah Velocity variation (test)Follow-184CVaR 0.05 ReturnRoML-2,702.88-2,048.94-1,395-741.06Jan 26, 2023Evaluation resultsMethodMethodLinksCVaR 0.05 ReturnRoMLBase Algorithm=VariBADBase Algorithm=VariBAD2023.01-184VariBAD2023.01-202PAIRED2023.01-725CVaR-ML2023.01-897RoMLBase Algorithm=PEARLBase Algorithm=PEARL2023.01-1,089PEARL2023.01-1,156CeSoR2023.01-2,606