episodes,rewards,steps 0,-0.5136373548809647,200 1,-0.5136373548809647,200 2,-0.5136373548809647,200 3,-0.5136373548809647,200 4,-0.5136373548809647,200 5,-0.5136373548809647,200 6,-0.5136373548809647,200 7,-0.5136373548809647,200 8,-0.5136373548809647,200 9,-0.5136373548809647,200