#stochastic optimal control
4 papers · 1 filter
Infinite horizon stochastic optimal control with sign-changing discount factor
Charles Bertucci, Jean-Michel Lasry, Pierre-Louis Lions
The paper analyzes an infinite‑horizon stochastic optimal control problem where the discount factor can be positive or negative depending on the state, using the associated Hamilto…
Is Deep Hedging Reinforcement Learning?
Frédéric Godin
The paper argues that the deep hedging framework, which trains neural network policies via Monte‑Carlo policy‑gradient methods to minimize risk measures, should be classified as re…
The optimal rate of convergence in mean field control via recoupled shadow flows
Sebastian Munoz
The paper establishes optimal convergence rates for the value functions of N‑particle stochastic optimal control problems towards their mean field control limit, using a novel reco…
Bang-Bang Evasion: Its Stochastic Optimality and a Terminal-Set-Based Implementation
Liraz Mudrik, Yaakov Oshman
The paper studies how a target can optimally evade a missile in a planar engagement under imperfect information and bounded controls, proving that bang‑bang maneuvers remain optima…