Build on our work
Our tools for susceptibilities, local learning coefficients, and SGMCMC sampling are open source in the devinterp library.
Work with us
Timaeus is now Resolution. Open roles are now posted on the Resolution careers page.
Stagewise Reinforcement Learning and the Geometry of the Regret Landscape
We extend singular learning theory to reinforcement learning, showing that phase transitions in policy development are governed by the local learning coefficient, which detects transitions even when policies appear identical in terms of regret.