I'd rather see it try to actually friggen BEAT Q*Bert without cheating or exploiting...I all have to say is thank God NES controllers are so light they bounce off CRT televisions...
As the trio describe in the paper, published on pre-print server arXiv, the agent was learning how to play Q*bert when it discovered an “interesting solution.” Normally, in Q*bert, players jump from cube to cube, with this action changing the platforms’ colors. Change all the colors (and dispatch some enemies), and you’re rewarded with points and sent to the next level. The AI found a better way, though:
First, it completes the first level and then starts to jump from platform to platform in what seems to be a random manner. For a reason unknown to us, the game does not advance to the second round but the platforms start to blink and the agent quickly gains a huge amount of points (close to 1 million for our episode time limit).
Artificial Intelligence is going to be popular for playing video games. But I don't ever try playing Q*bert because this game be played on a very few platform. I used generally PC to play my online video games.