ResearchBenchmarksLocomotion on MuJoCo Walker t = 3T/4Follow631.6Average ReturnDQUCB370.664438.407506.15573.893Oct 3, 2025Evaluation ResultsMethodMethodLinksAverage ReturnDQUCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10631.6DQN-UCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10433.3DQNT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10380.7