New Framework for Stochastic Optimal Control and Option Pricing

This paper delves into the theoretical underpinnings of stochastic optimal control in discrete time, proposing a novel dynamic programming framework. It introduces methods for estimating the value function using nonparametric regression within reproducing kernel Hilbert spaces and Monte Carlo subsampling. The research focuses on analyzing how errors propagate backward through time, a less-explored area in the field, and demonstrates its application to pricing American options. AI

IMPACT Introduces novel methods for value function estimation in stochastic control, potentially impacting AI applications in finance and decision-making under uncertainty.

RANK_REASON Academic paper on theoretical foundations of stochastic optimal control and its application to financial modeling. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• Andrea Della Vecchia
• arXiv
• knowledge representation and reasoning
• reproducing kernel Hilbert space

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →