Catastrophic-risk-aware reinforcement learning with extreme-value-theory-based policy gradients

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Davar, Parisa, Godin, Frédéric, Garrido, Jose
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909233155407872
author Davar, Parisa
Godin, Frédéric
Garrido, Jose
author_facet Davar, Parisa
Godin, Frédéric
Garrido, Jose
contents This paper tackles the problem of mitigating catastrophic risk (which is risk with very low frequency but very high severity) in the context of a sequential decision making process. This problem is particularly challenging due to the scarcity of observations in the far tail of the distribution of cumulative costs (negative rewards). A policy gradient algorithm is developed, that we call POTPG. It is based on approximations of the tail risk derived from extreme value theory. Numerical experiments highlight the out-performance of our method over common benchmarks, relying on the empirical distribution. An application to financial risk management, more precisely to the dynamic hedging of a financial option, is presented.
format Preprint
id arxiv_https___arxiv_org_abs_2406_15612
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Catastrophic-risk-aware reinforcement learning with extreme-value-theory-based policy gradients
Davar, Parisa
Godin, Frédéric
Garrido, Jose
Machine Learning
Risk Management
This paper tackles the problem of mitigating catastrophic risk (which is risk with very low frequency but very high severity) in the context of a sequential decision making process. This problem is particularly challenging due to the scarcity of observations in the far tail of the distribution of cumulative costs (negative rewards). A policy gradient algorithm is developed, that we call POTPG. It is based on approximations of the tail risk derived from extreme value theory. Numerical experiments highlight the out-performance of our method over common benchmarks, relying on the empirical distribution. An application to financial risk management, more precisely to the dynamic hedging of a financial option, is presented.
title Catastrophic-risk-aware reinforcement learning with extreme-value-theory-based policy gradients
topic Machine Learning
Risk Management
url https://arxiv.org/abs/2406.15612