Tag
This paper advocates using category theory and environmental groupoids to structure reinforcement learning in partially observable environments, leveraging symmetries for improved sample efficiency and generalization.
Physicists have advanced fluid theory by developing a new approach based on symmetries, extending beyond the Navier-Stokes equations and incorporating microscopic particle behaviors.
This paper argues that the bulk of near-zero Hessian eigenvalues in neural networks arises from weakly broken symmetries of the network parametrization, showing that high-curvature directions are orthogonal to the symmetry subspace while the bulk lies within it.