ResearchBenchmarksMeta-Reinforcement Learning on MuJoCo HalfCheetah 10D-task (b) (test)Meta-Reinforcement Learning on MuJoCo HalfCheetah 10D-task (b) (test)Follow1,697CVaR0.05 ReturnRoML78.76498.889191,339.12Jan 26, 2023Evaluation resultsMethodMethodLinksCVaR0.05 ReturnRoMLBase Algorithm=VariBADBase Algorithm=VariBAD2023.011,697RoMLBase Algorithm=PEARLBase Algorithm=PEARL2023.011,657PEARL2023.011,623VariBAD2023.011,536CeSoR2023.01981PAIRED2023.01354CVaR-ML2023.01141