Measuring Value Alignment
Fazl Barez; Philip Torr · 2023 · arXiv (Cornell University) background low priority queued
Main argument
None
Why it matters here
None
Reading notes
MDP formalism for quantifying alignment — technical counterpart to Peterson-Gardenfors measurement; assumes values already specified (the gap the dissertation presses).
Fazl Barez; Philip Torr (2023). Measuring Value Alignment. arXiv (Cornell University). https://doi.org/10.48550/arXiv.2312.15241