ResearchBenchmarksMeta-Reinforcement Learning on MuJoCo HalfCheetah Mass variation (test)Meta-Reinforcement Learning on MuJoCo HalfCheetah Mass variation (test)Follow1,259CVaR 0.05 ReturnRoML-10.84318.83648.5978.17Jan 26, 2023Evaluation resultsMethodMethodLinksCVaR 0.05 ReturnRoMLBase Algorithm=VariBADBase Algorithm=VariBAD2023.011,259RoMLBase Algorithm=PEARLBase Algorithm=PEARL2023.011,186PEARL2023.011,115VariBAD2023.011,072CeSoR2023.01902PAIRED2023.01438CVaR-ML2023.0138