
ep5 - Sean Meyn: Markov chains, networks, reinforcement learning, beekeeping and jazz
inControl
00:00
The Future of Control and Rearrangement Learning
I'm hopeful that the fact that so many people jumping into RL will expand the field and there won't be just two algorithms. We need, you know, way more diverse ways of thinking about what is RL. It's now, we don't have to be so extreme. You know, we can put everything together. Take all the wonderful concepts from reinforced millenie and control, put them together and come with something much, much better than either domain. So that's what might say dream. I mean, we'll see.
Transcript
Play full episode