ResearchBenchmarksLocomotion on MuJoCo Walker (t = T)Follow755Average ReturnDQUCB465.88540.94616691.06Oct 3, 2025Evaluation ResultsMethodMethodLinksAverage ReturnDQUCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10755DQN-UCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10595DQNT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10477