ResearchBenchmarksRobotic Manipulation on FetchPickAndPlace v1Robotic Manipulation on FetchPickAndPlace v1Follow18Time to Threshold (Epochs)ACDC15.3233.4151.569.59Mar 2, 2026Evaluation resultsMethodMethodLinksTime to Threshold (Epochs)Cumulative RegretACDCThreshold (θ)=0.90Threshold (θ)=0.902026.031818.2HERThreshold (θ)=0.90Threshold (θ)=0.902026.033538.5DTGSHThreshold (θ)=0.90Threshold (θ)=0.902026.034041.2CHERThreshold (θ)=0.90Threshold (θ)=0.902026.034245.3HEREBPThreshold (θ)=0.90Threshold (θ)=0.902026.038548.5