The Evolution Strategies Paradox: Better Models from Worse Perturbations
This paper characterizes the paradox, then examines how the local reward landscape and properties of the ES estimator contribute to it: in high-dimensional spaces, exploration leads to worse performance, yet still highlights good directions; aggregating those directions then allows for making local improvements.
Roberto Dailey, Kajetan Schweighofer, Jamieson Warner et al.
· 0 citations