ResearchBenchmarksLocomotion on MuJoCo Walker t = T/2 (shift)Follow323.8Average ReturnDQUCB287.088296.619306.15315.681Oct 3, 2025Evaluation ResultsMethodMethodLinksAverage ReturnDQUCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10323.8DQN-UCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10323.3DQNT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10288.5