ResearchBenchmarksOffline Reinforcement Learning on K2D13-250-5-midFollow0.75NAUCIC-CQL0.50040.56520.630.6948Feb 24, 2025Evaluation ResultsMethodMethodLinksNAUCIC-CQL2025.020.75IC-IQL2025.020.71AD2025.020.53IC-DQN2025.020.51