In 2013, a group of researchers wanted to create an AI system that could beat every Atari game. They developed a system called Deep Q Networks (DQN) and less than two years later, it was superhuman. But there was one notable exception. When playing Montezuma’s Revenge, DQN couldn’t score a single point. What was it that made this game so vexingly difficult for AI? Brian Christian investigates.
[TED Ed]
A fantastic cartoon by artist Kerry Callen: Btw, the objects on the bottom of page…
For today’s edition of “Deal of the Day,” here are some of the best deals…
Few Star Wars characters are as despised as Jar Jar Binks, but even though almost…
https://youtu.be/AVHuvI0fbTI?si=QUDn02ygm9j5yoMr From Wired: Psychiatrist Dr. Eric Bender answers your questions about mental health from Twitter.…