ResearchBenchmarksLocomotion on MuJoCo Halfcheetah (t = 3T/4)Follow2,293.6Average ReturnDQUCB1,781.0881,914.1442,047.22,180.256Oct 3, 2025Evaluation ResultsMethodMethodLinksAverage ReturnDQUCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.102,293.6DQN-UCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.101,920.7DQNT=200000, Action Bins...T=200000, Action Bins (K)=1002025.101,800.8