ResearchBenchmarksOffline Reinforcement Learning on D4RL Cheetah Stochastic MuJoCo (Mixed)Offline Reinforcement Learning on D4RL Cheetah Stochastic MuJoCo (Mixed)Follow396.4Mean ReturnCODAC-C206.808256.029305.25354.471Jul 12, 2021Evaluation resultsMethodMethodLinksMean ReturnCVaR 0.1CODAC-Cobjective=CVaRobjective=CVaR2021.07396.4238.5CODAC-CObjective=Risk-sensitiveObjective=Risk-sensitive2021.07396.4238.5CODAC-Nobjective=risk-neutralobjective=risk-neutral2021.07347.7149.2CODAC-NObjective=Risk-neutralObjective=Risk-neutral2021.07347.7149.2ORAAC2021.07307.1118.9ORAAC2021.07307.1118.9CQL2021.07214.112CQL2021.07214.112