ResearchBenchmarksLocomotion on MuJoCo Hopper t = 3T/4Follow516.4Average ReturnDQUCB286.456346.153405.85465.547Oct 3, 2025Evaluation ResultsMethodMethodLinksAverage ReturnDQUCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10516.4DQN-UCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10331.1DQNT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10295.3