Risk-Averse Reinforcement Learning with Itakura-Saito Loss

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Udovichenko, Igor, Croissant, Olivier, Toleutaeva, Anita, Burnaev, Evgeny, Korotin, Alexander
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909622983458816
author Udovichenko, Igor
Croissant, Olivier
Toleutaeva, Anita
Burnaev, Evgeny
Korotin, Alexander
author_facet Udovichenko, Igor
Croissant, Olivier
Toleutaeva, Anita
Burnaev, Evgeny
Korotin, Alexander
contents Risk-averse reinforcement learning finds application in various high-stakes fields. Unlike classical reinforcement learning, which aims to maximize expected returns, risk-averse agents choose policies that minimize risk, occasionally sacrificing expected value. These preferences can be framed through utility theory. We focus on the specific case of the exponential utility function, where one can derive the Bellman equations and employ various reinforcement learning algorithms with few modifications. To address this, we introduce to the broad machine learning community a numerically stable and mathematically sound loss function based on the Itakura-Saito divergence for learning state-value and action-value functions. We evaluate the Itakura-Saito loss function against established alternatives, both theoretically and empirically. In the experimental section, we explore multiple scenarios, some with known analytical solutions, and show that the considered loss function outperforms the alternatives.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16925
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Risk-Averse Reinforcement Learning with Itakura-Saito Loss
Udovichenko, Igor
Croissant, Olivier
Toleutaeva, Anita
Burnaev, Evgeny
Korotin, Alexander
Machine Learning
Risk-averse reinforcement learning finds application in various high-stakes fields. Unlike classical reinforcement learning, which aims to maximize expected returns, risk-averse agents choose policies that minimize risk, occasionally sacrificing expected value. These preferences can be framed through utility theory. We focus on the specific case of the exponential utility function, where one can derive the Bellman equations and employ various reinforcement learning algorithms with few modifications. To address this, we introduce to the broad machine learning community a numerically stable and mathematically sound loss function based on the Itakura-Saito divergence for learning state-value and action-value functions. We evaluate the Itakura-Saito loss function against established alternatives, both theoretically and empirically. In the experimental section, we explore multiple scenarios, some with known analytical solutions, and show that the considered loss function outperforms the alternatives.
title Risk-Averse Reinforcement Learning with Itakura-Saito Loss
topic Machine Learning
url https://arxiv.org/abs/2505.16925