ResearchBenchmarksLocomotion on MuJoCo Walker t = 2T/3 (shift)Follow411.6Average ReturnDQUCB315.4340.375365.35390.325Oct 3, 2025Evaluation ResultsMethodMethodLinksAverage ReturnDQUCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10411.6DQN-UCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10367DQNT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10319.1