Fig. 5From: A reinforcement learning approach for protein–ligand binding pose predictionTwo searching paths in \(18\times 18\times 18\) cubic boxes during the training process for the Cu-ligand dataset. Left: The searching path in episode 10,000. Right: The searching path in episode 20,000. The red point is the start ligand site, the green point is the true ligand site, and the blue path is the searching path. Environment atoms are not presented in plotsBack to article page