ResearchBenchmarksOffline Reinforcement Learning on HalfCheetah Medium Delayed Reward (D4RL)Follow42.9ScoreISCT-0.67610.63721.9533.263Feb 12, 2026Evaluation ResultsMethodMethodLinksScoreISCTReward Type=DelayedReward Type=Delayed2026.0242.9QDTReward Type=DelayedReward Type=Delayed2026.0242.4DTReward Type=DelayedReward Type=Delayed2026.0242.2CQLReward Type=DelayedReward Type=Delayed2026.021