ResearchBenchmarksOffline Reinforcement Learning on Stochastic D4RL Hopper MuJoCo (Mixed)Offline Reinforcement Learning on Stochastic D4RL Hopper MuJoCo (Mixed)Follow1,551.2Mean ReturnCODAC-C134.72502.46870.21,237.94Jul 12, 2021Evaluation resultsMethodMethodLinksMean ReturnCVaR 0.1 ReturnCODAC-Cobjective=CVaRobjective=CVaR2021.071,551.21,449.6CODAC-CObjective=Risk-sensitiveObjective=Risk-sensitive2021.071,551.21,449.6CODAC-Nobjective=risk-neutralobjective=risk-neutral2021.071,483.91,457.6CODAC-NObjective=Risk-neutralObjective=Risk-neutral2021.071,483.91,457.6ORAAC2021.07876.3524.9ORAAC2021.07876.3524.9CQL2021.07189.2-21.4CQL2021.07189.2-21.4