Fig. 7
From: A reinforcement learning approach for protein–ligand binding pose prediction
Four cases of the critic distances and the real distance in the training process for Cu-ligand dataset. Upper left: Episode 10,000. Upper right: Episode 13,000. Lower left: Episode 16,000. Lower right: Episode 20,000. The red curve is the critic model predicted distance between the current state and the true ligand site. The blue curve is the real distance between the current state and the true ligand site. The X-axis denotes the step number in the episode and the Y-axis denotes the distance value