RLS Reinforcement Learning

When I first picked up Richard Sutton's reinforcement learning book, before sort of this deep learning, RLS seemed to me like magic. The kind of part of that is, why is RL? Why does it need so many samples, so many experiences to learn from? Because really what's happening is when you have a sparse reward, you do something, maybe for luck. Some might have been good and bad in either one. And so that's why I needed so many experiences. But once you have enough experiences, effectively RL is teasing that apart. It's starting to say, OK, what is consistently there when you get a higher reward? And what's consistently there when we get a