Saved in:
Bibliographic Details
Main Author: Xu, Chen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.24280
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910169237028864
author Xu, Chen
author_facet Xu, Chen
contents We present a framework using Relative Entropy Inverse Reinforcement Learning (RE-IRL) to recover investor reward functions from observed investment actions and market conditions. Unlike traditional IRL algorithms, RE-IRL is employed to account for environments where transition probabilities are unknown or inaccessible. To address the challenge of data sparsity, we utilize a $K$-nearest neighbor approach to estimate the observed behavior policy. Furthermore, we propose a statistical testing framework to evaluate the validity and robustness of the estimated results.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24280
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Model-Free Inference of Investor Preferences: A Relative Entropy IRL Approach
Xu, Chen
Machine Learning
We present a framework using Relative Entropy Inverse Reinforcement Learning (RE-IRL) to recover investor reward functions from observed investment actions and market conditions. Unlike traditional IRL algorithms, RE-IRL is employed to account for environments where transition probabilities are unknown or inaccessible. To address the challenge of data sparsity, we utilize a $K$-nearest neighbor approach to estimate the observed behavior policy. Furthermore, we propose a statistical testing framework to evaluate the validity and robustness of the estimated results.
title Model-Free Inference of Investor Preferences: A Relative Entropy IRL Approach
topic Machine Learning
url https://arxiv.org/abs/2604.24280