The basic dynamics of the game are still in the place, well, one can see the pac man can be seen
eating the pellets, avoid the ghosts and try not to die.
Nvidia is well known for all the graphics cards, but at the same time, the company also invests a lot
of time into developing and working into artificial intelligence (AI) and hence, their latest projects
has been an AI system which has recreated the Pac-Man game by simply watching the game being
We should also mention here that this software did not put into use any coding or any pre-rendered
images. What the AI system does is that worked on the visual data of the game and it can be played
along with the all the accompanying controller inputs. Nvidia has plans in place to release it online in
the near future.
Also, we have to mention here that this AI version is far from perfect, the images which can be seen
are blurry and that the AI has not been able to “capture the exact behaviour of the game’s ghosts,
each of which is programmed with a specific personality that dictates its movement”.
However, the basic dynamics of the game are still in the place, well, one can see the pac man can be
seen eating the pellets, avoid the ghosts and try not to die.
“It learns all of these things just by watching,” Nvidia’s Rev Lebaredian, vice president of simulation
technology, told journalists in a briefing.
“[It’s] similar to how a human programmer can watch many episodes of Pac-Man on YouTube and
infer what the rules of the games are and reconstruct them,” Lebaredian further added.
Lebaredian went on to add “the work had been done in collaboration with Pac-Man’s creator,
Bandai Namco, which celebrated the 40th anniversary of the arcade classic yesterday (May 22)”.
Nvidia also says that the works drive home the point that the artificial intelligence can be used for
game design in the future. All the developers can put their work into the AI and then, these can be
used to create variations or design new levels.
“You could use this to mash different games together, giving additional power to games developers
by [letting them] blend together different games,” Sanja Fidler, director of Nvidia’s Toronto research