Diffractor

Diffractor is the first author of this paper. Official title: "Regret Bounds for Robust Online Decision Making" > Abstract: We propose a framework which generalizes "decision making with structured observations" by allowing robust (i.e. multivalued) models. In this framework, each model associates each decision with a convex set of probability...

One of the primary conceptual challenges of UDT is that, if future-you is going to be deferring to past-you about what to do in various circumstances, and past-you hasn't exhaustively thought through every possible circumstance ahead of time, that causes a tension. In order for deferring to past-you to produce...

This is the post with some needed concepts and discussion that didn't cleanly fit into any other section, so it might be a bit of a rambly mess. Specifically, this post splits into two parts. One is assorted musings about when to defer to past-you vs current-you when making decisions,...

The Omnipresence of Unplanned Observations Time to introduce some more concepts. If an observation is "any data you can receive which affects your actions", then there seem to be two sorts of observations. A plannable observation is the sort of observation where you could plan ahead of time how to...

Attention Conservation Notice: This is a moderately mathy post. Affineness, it's Useful! So, if we're going to be restricting the sorts of environments we're considering, and trying to build an algorithm that's closer to UDT1.0 (just pick your action to optimize global utility without the whole "coordinating with alternate versions...

We now resume your regularly scheduled LessWrong tradition of decision theory posting. This is a sequence, be sure to note. Just the first and last post will be on Alignment Forum, and the whole thing will be linked together. Epistemic Status: This is mostly just recapping old posts so far....

Proposition 1: Given some compact metric space of options X, if U:X→R is a bounded function, {μ|∀ν∈ΔX:μ(U)≥ν(U)}=Δ{x|∀y∈X:U(x)≥U(y)} PROOF: To do this, we must show that anything in the first set is in the second, and vice-versa. So, assume μ is in the first set. Then for any ν, ν(U)≤μ(U). However,...