Armin Sommer
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization
A preprint studies what happens to the intended goal in agents that misgeneralize, finding three forms of policy-goal misalignment across three Procgen environments and five robot tasks, and testing steering and rewiring fixes.