ResearchBenchmarksLocomotion on MuJoCo Hopper (t = T)Follow689.6Average ReturnDQUCB399.024474.462549.9625.338Oct 3, 2025Evaluation ResultsMethodMethodLinksAverage ReturnDQUCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10689.6DQN-UCBT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10509DQNT=200000, Action Bins...T=200000, Action Bins (K)=1002025.10410.2