In other words, the headline is sensational because the authors didn't understand how the hardware works.
b) Game Settings: A state was represented by the most recent frame, which was a 60 × 45 3-channel RGB image. The number of skipped frames is controlled by the skipcount parameter. We experimented with skipcounts of 0-7, 10, 15, 20, 25, 30, 35 and 40. It is important to note that the agent repeats the last decision on the skipped frames.
How is this not using the screen buffer?
"Probably the best operating system in the world is the [operating system] made for the PDP-11 by Bell Laboratories." - Ted Nelson, October 1977