ResearchBenchmarksRobotic Manipulation on HandReach v0Robotic Manipulation on HandReach v0Follow44.1Cumulative RegretACDC42.5852.8463.173.36Mar 2, 2026Evaluation resultsMethodMethodLinksCumulative RegretTime to Threshold (Epochs)ACDCThreshold (θ)=0.50Threshold (θ)=0.502026.0344.15DTGSHThreshold (θ)=0.50Threshold (θ)=0.502026.0360.535HERThreshold (θ)=0.50Threshold (θ)=0.502026.0368.265HEREBPThreshold (θ)=0.50Threshold (θ)=0.502026.0375.2—CHERThreshold (θ)=0.50Threshold (θ)=0.502026.0382.1—