This is just a variance reduction technique. The value function, the function that takes a board and tells you the probability that white will win. This is just equivalent to what would happen if you played out from that position infinite number of times. But using the value function is going to be lower variance. Does that make sense? Right. You do things like this a whole bunch of other places in reinforcement learning as well. And I think this is probably the cleanest example of a like variance reduction approach.
Read the full transcript here.
How hard is it to arrive at true beliefs about the world? How can you find enjoyment in being wrong? When presenting claims that will be scrutinized by others, is it better to hedge and pad the claims in lots of caveats and uncertainty, or to strive for a tone that matches (or perhaps even exaggerates) the intensity with which you hold your beliefs? Why should you maybe focus on drilling small skills when learning a new skill set? What counts as a "simple" question? How can you tell when you actually understand something and when you don't? What is "cargo culting"? Which features of AI are likely in the future to become existential threats? What are the hardest parts of AI research? What skills will we probably really wish we had on the eve of deploying superintelligent AIs?
Buck Shlegeris is the CTO of Redwood Research, an independent AI alignment research organization. He currently leads their interpretability research. He previously worked on research and outreach at the Machine Intelligence Research Institute. His website is shlegeris.com.
Staff
Music
Affiliates