3 papers
math.OC2023
A Large Deviations Perspective on Policy Gradient Algorithms
Wouter Jongeneel, Daniel Kuhn, Mengmeng Li
Motivated by policy gradient methods in the context of reinforcement learning, we identify a large deviation rate function for the iterates generated by stochastic gradient descent…
math.DS2023
On topological properties of compact attractors on Hausdorff spaces
Wouter Jongeneel
We characterize when a compact, invariant, asymptotically stable attractor on a locally compact Hausdorff space is a strong deformation retract of its domain of attraction.
math.OC2023
On continuation and convex Lyapunov functions
Wouter Jongeneel, Roland Schwan
Suppose that the origin is globally asymptotically stable under a set of continuous vector fields on Euclidean space and suppose that all those vector fields come equipped with --…