38 citations · 80 across the 10 of their papers we have counts for
3 papers · 1 filter
Interpreting Reinforcement Learning Agents with Susceptibilities
Chris Elliott, Einar Urdshals, David Quarel +1
Susceptibilities are a technique for neural network interpretability that studies the response of posterior expectation values of observables to perturbations of the loss. We gener…
Stagewise Reinforcement Learning and the Geometry of the Regret Landscape
Chris Elliott, Einar Urdshals, David Quarel +2
Singular learning theory characterizes Bayesian learning as an evolving tradeoff between accuracy and complexity, with transitions between qualitatively different solutions as samp…
Structure Development in List-Sorting Transformers
Einar Urdshals, Jasmina Urdshals
We study how a one-layer attention-only transformer develops relevant structures while learning to sort lists of numbers. At the end of training, the model organizes its attention…