ResearchBenchmarksOffline Reinforcement Learning on D4RL Walker2d Stochastic MuJoCo (Mixed)Offline Reinforcement Learning on D4RL Walker2d Stochastic MuJoCo (Mixed)Follow450Mean ReturnCODAC-C59.272160.711262.15363.589Jul 12, 2021Evaluation resultsMethodMethodLinksMean ReturnCVaR 0.1CODAC-Cobjective=CVaRobjective=CVaR2021.07450261.4CODAC-CObjective=Risk-sensitiveObjective=Risk-sensitive2021.07450261.4CODAC-Nobjective=risk-neutralobjective=risk-neutral2021.07358.7106.4CODAC-NObjective=Risk-neutralObjective=Risk-neutral2021.07358.7106.4ORAAC2021.07222-69.6ORAAC2021.07222-69.6CQL2021.0774.3-64CQL2021.0774.3-64