
Episode 04: Joel Lehman, OpenAI, on evolution, open-endedness, and reinforcement learning
Generally Intelligent
00:00
Machine Learning
There are numerous examples of technologies where the potential of them was not immediately evident at the time. It's hard to predict what kind of idea s will eventually end up succeeding in the market place of research. I try to come over with ideas in research that will be evergreen, might not depend on the specific technology. The philosophy behind novelly search is still relevant to the field a deep reinforcement learning. No matter what youare dealing with, small norl thatworks, or big nora nhet works.
Transcript
Play full episode