cs.LG, math.OC, q-fin.CP, q-fin.MF, q-fin.RM

SNAPO: Smooth Neural Adjoint Policy Optimization for Optimal Control via Differentiable Simulation

arXiv:2605.06570v1 Announce Type: new
Abstract: Many real-world problems require sequential decisions under uncertainty: when to inject or withdraw gas from storage, how to rebalance a pension portfolio each month, what temperature profile to run thro…