ResearchBenchmarksLocomotion on MuJoCo Halfcheetah (t = T)Follow2,694.9Average ReturnDQUCB1,938.0922,134.5712,331.052,527.529Oct 3, 2025Evaluation ResultsMethodMethodLinksAverage ReturnDQUCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.102,694.9DQN-UCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.102,125DQNT=200000, Action Bins...T=200000, Action Bins (K)=1002025.101,967.2