ResearchBenchmarksOffline Reinforcement Learning on Stochastic D4RL Walker2d Medium MuJoCoOffline Reinforcement Learning on Stochastic D4RL Walker2d Medium MuJoCoFollow1,537.3Mean ReturnCODAC-N1,104.141,216.5951,329.051,441.505Jul 12, 2021Evaluation resultsMethodMethodLinksMean ReturnCVaR (0.1)CODAC-Nobjective=risk-neutralobjective=risk-neutral2021.071,537.31,158.8CODAC-NObjective=Risk-neutralObjective=Risk-neutral2021.071,537.31,158.8CQL2021.071,524.31,343.8CQL2021.071,524.31,343.8ORAAC2021.071,134.1663ORAAC2021.071,134.1663CODAC-Cobjective=CVaRobjective=CVaR2021.071,120.8902.3CODAC-CObjective=Risk-sensitiveObjective=Risk-sensitive2021.071,120.8902.3