Saved in:
Bibliographic Details
Main Author: Moustakides, George V.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.13189
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916329279193088
author Moustakides, George V.
author_facet Moustakides, George V.
contents When the underlying conditional density is known, conditional expectations can be computed analytically or numerically. When, however, such knowledge is not available and instead we are given a collection of training data, the goal of this work is to propose simple and purely data-driven means for estimating directly the desired conditional expectation. Because conditional expectations appear in the description of a number of stochastic optimization problems with the corresponding optimal solution satisfying a system of nonlinear equations, we extend our data-driven method to cover such cases as well. We test our methodology by applying it to Optimal Stopping and Optimal Action Policy in Reinforcement Learning.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13189
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Data-Driven Estimation of Conditional Expectations, Application to Optimal Stopping and Reinforcement Learning
Moustakides, George V.
Machine Learning
60J20, 68T07
When the underlying conditional density is known, conditional expectations can be computed analytically or numerically. When, however, such knowledge is not available and instead we are given a collection of training data, the goal of this work is to propose simple and purely data-driven means for estimating directly the desired conditional expectation. Because conditional expectations appear in the description of a number of stochastic optimization problems with the corresponding optimal solution satisfying a system of nonlinear equations, we extend our data-driven method to cover such cases as well. We test our methodology by applying it to Optimal Stopping and Optimal Action Policy in Reinforcement Learning.
title Data-Driven Estimation of Conditional Expectations, Application to Optimal Stopping and Reinforcement Learning
topic Machine Learning
60J20, 68T07
url https://arxiv.org/abs/2407.13189