In this paper, we proposed a method by which a stereo vision-based mobile robot learns to reach a target by detecting and avoiding occlusions. We call the internal representation that describes the learned behavior \stereo sketch." First, an input scene is segmented into homogeneous regions by the enhanced ISODATA algorithm with MDL principle in terms of image coordinates and disparity information obtained from the fast stereo matcher based on the coarse-tone control method. Then, in terms of the segmented regions including the target area and their occlusion status identi ed during the stereo and motion disparity estimation process, we construct a state space for a reinforcement learning method to obtain target reaching behavior. As a result, the robot can avoid obstacles without explicitly describing them. We give the computer simulation results and real robot implementation to show the validity of our method.