ResearchBenchmarksOffline Reinforcement Learning on Stochastic D4RL Cheetah MuJoCo (Medium)Offline Reinforcement Learning on Stochastic D4RL Cheetah MuJoCo (Medium)Follow361.4Mean ReturnORAAC20.072108.686197.3285.914Jul 12, 2021Evaluation resultsMethodMethodLinksMean ReturnCVaR 0.1ORAAC2021.07361.491.3ORAAC2021.07361.491.3CODAC-Nobjective=risk-neutralobjective=risk-neutral2021.07338-41CODAC-NObjective=Risk-neutralObjective=Risk-neutral2021.07338-41CODAC-Cobjective=CVaRobjective=CVaR2021.07335-27CODAC-CObjective=Risk-sensitiveObjective=Risk-sensitive2021.07335-27CQL2021.0733.2-15CQL2021.0733.2-15