New Kind of Memory for AI

AI researchers have typically tried to get around the issues posed by by Montezuma’s Revenge and Pitfall! by instructing reinforcement-learning algorithms to explore randomly at times, while adding rewards for exploration—what’s known as “intrinsic motivation.” But the Uber researchers believe this fails to capture an important aspect of human curiosity. “We hypothesize that a major weakness of current intrinsic motivation algorithms is detachment,” they write. “Wherein the a...

 Human Memory, Computer Memory

Almost all of those limits start with a peculiar fact about human memory: Although we are pretty good at storing information in our brains, we are pretty poor at retrieving it. We can recognize photos from our high school yearbooks decades later, yet find it impossible to remember what we had for breakfast yesterday. Faulty memories have been known to lead to erroneous eyewitness testimony (and false imprisonment), to marital friction (in the form of overlooked anniversaries), and even death ...