How to Be a Successful PhD Student

John Defterios: I was in the right place at the right time. So it's like hard to replicate the exact initial conditions, even if I were to redo it myself. First couple of years, I just worked on things that I just tried to do,. Like achieve cool things in those domains. Then I guess like deep learning started to take off. And so I had a little bit of a, maybe it had like a mid life crisis, mid DHD crisis. He then decided to go into work on Deep RL.