Month: October 2016

Is Reinforcement Learning (RL) a fantasy?

Can a future artificial intelligences be made safe? And assuming AI Safety is feasible at all, will it turn out to be an easy problem to solve, or an extremely hard problem? Right now, there is a feeding frenzy under way (Jaan Talinn called it an “ecosystem”), involving a number of groups and individuals who want to persuade charities to give them money …