3 papers
cs.LG2026
Continuous-time Optimal Stopping through Deep Reinforcement Learning
Cosmin Borsa, Michael Ludkovski
Simulation based solvers for optimal stopping problems must discretize the stopping decision. Under classical dynamic programming, a coarse exercise grid with only a few stopping o…
math.NA2025
DeepPAAC: A New Deep Galerkin Method for Principal-Agent Problems
Michael Ludkovski, Changgen Xie, Zimu Zhu
We consider numerical resolution of principal-agent (PA) problems in continuous time. We formulate a generic PA model with continuous and lump payments and a multi-dimensional stra…
stat.AP2025
Functional Analysis of Loss-development Patterns in P&C Insurance
Arthur Charpentier, Qiheng Guo, Mike Ludkovski
We analyze loss development in NAIC Schedule P loss triangles using functional data analysis methods. Adopting the functional viewpoint, our dataset comprises 3300+ curves of incre…