I’ve started thinking in this direction already backin 2016, and more in 2018 but only this year Alex and I nailed the precise definitions that make everything come together, and derived some key foundational theorems. Of course, much work yet remains.
After reading some of your paper, I think that they are actually very different. IIUC, you are talking about pessimism as a method to avoid traps, but you assume realizability. On the other hand, infra-Bayesianism is (to first approximation) orthogonal to dealing with traps, instead it allows dealing with nonrealizability.
The results I prove assume realizability, and some of the results are about traps, but independent of the results, the algorithm for picking actions resembles infra-Bayesianism. So I think we’re taking similar objects and proving very different sorts of things.
Looks like we’ve been thinking along very similar lines! https://www.lesswrong.com/posts/RzAmPDNciirWKdtc7/pessimism-about-unknown-unknowns-inspires-conservatism
Thanks, I’ll make sure to read it!
I’ve started thinking in this direction already back in 2016, and more in 2018 but only this year Alex and I nailed the precise definitions that make everything come together, and derived some key foundational theorems. Of course, much work yet remains.
After reading some of your paper, I think that they are actually very different. IIUC, you are talking about pessimism as a method to avoid traps, but you assume realizability. On the other hand, infra-Bayesianism is (to first approximation) orthogonal to dealing with traps, instead it allows dealing with nonrealizability.
The results I prove assume realizability, and some of the results are about traps, but independent of the results, the algorithm for picking actions resembles infra-Bayesianism. So I think we’re taking similar objects and proving very different sorts of things.
Well, I agree that both formalisms use maximin so there might be some way to merge them. It’s definitely something to think about.