3 papers
cs.LG2025
Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs
Daniel Furelos-Blanco, Charles Pert, Frederik Kelbel +3
Training general agents to follow complex instructions (tasks) in intricate environments (levels) remains a core challenge in reinforcement learning. Random sampling of task-level…
math.OC2025
An Inexact Tensor-Train Primal-Dual Interior-Point Method for Semidefinite Programs
Frederik Kelbel, Sergey Dolgov, Dante Kalise +1
In this work, we introduce an interior-point method that employs tensor decompositions to efficiently represent and manipulate the variables and constraints of semidefinite program…
cs.LG2024
Optimal Control of Agent-Based Dynamics under Deep Galerkin Feedback Laws
Frederik Kelbel
Ever since the concepts of dynamic programming were introduced, one of the most difficult challenges has been to adequately address high-dimensional control problems. With growing…