ResearchBenchmarksReinforcement Learning target performance estimation on K2D9 1000-5-lateFollow0.86NAUCIC-CQL0.7040.74450.7850.8255Feb 24, 2025Evaluation ResultsMethodMethodLinksNAUCIC-CQL2025.020.86IC-IQL2025.020.84AD2025.020.82IC-DQN2025.020.71