Reinforcement Learning Does Work

Deep reinforcement learning is based on the idea that a deep nural network can analyze causality for you. But without an understanding of causality, we can't already understand why rainboso lerning works. In science in general, there's a long history of humans discovering techniques which work before actually understanding why they work. And i kind of likened that bit to reinforcement learning. Maybe that you have a process which does work but it's a bit mysterious,. maybe to do certain things to get it to work, but the actual understanding as to why it works isn't they.