ResearchBenchmarksOffline Reinforcement Learning on K2D13 1000-5-midFollow0.91NAUCIC-CQL0.74360.78680.830.8732Feb 24, 2025Evaluation ResultsMethodMethodLinksNAUCIC-CQL2025.020.91IC-IQL2025.020.91AD2025.020.87IC-DQN2025.020.75