Guardado en:
Detalles Bibliográficos
Autores principales: Kato, Masahiro, Nakagawa, Kei, Abe, Kenshi, Morimura, Tetsuro, Baba, Kentaro
Formato: Preprint
Publicado: 2020
Materias:
Acceso en línea:https://arxiv.org/abs/2010.01404
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912116440563712
author Kato, Masahiro
Nakagawa, Kei
Abe, Kenshi
Morimura, Tetsuro
Baba, Kentaro
author_facet Kato, Masahiro
Nakagawa, Kei
Abe, Kenshi
Morimura, Tetsuro
Baba, Kentaro
contents This study investigates the mean-variance (MV) trade-off in reinforcement learning (RL), an instance of the sequential decision-making under uncertainty. Our objective is to obtain MV-efficient policies whose means and variances are located on the Pareto efficient frontier with respect to the MV trade-off; under the condition, any increase in the expected reward would necessitate a corresponding increase in variance, and vice versa. To this end, we propose a method that trains our policy to maximize the expected quadratic utility, defined as a weighted sum of the first and second moments of the rewards obtained through our policy. We subsequently demonstrate that the maximizer indeed qualifies as an MV-efficient policy. Previous studies that employed constrained optimization to address the MV trade-off have encountered computational challenges. However, our approach is more computationally efficient as it eliminates the need for gradient estimation of variance, a contributing factor to the double sampling issue observed in existing methodologies. Through experimentation, we validate the efficacy of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2010_01404
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Mean-Variance Efficient Reinforcement Learning with Applications to Dynamic Financial Investment
Kato, Masahiro
Nakagawa, Kei
Abe, Kenshi
Morimura, Tetsuro
Baba, Kentaro
Machine Learning
This study investigates the mean-variance (MV) trade-off in reinforcement learning (RL), an instance of the sequential decision-making under uncertainty. Our objective is to obtain MV-efficient policies whose means and variances are located on the Pareto efficient frontier with respect to the MV trade-off; under the condition, any increase in the expected reward would necessitate a corresponding increase in variance, and vice versa. To this end, we propose a method that trains our policy to maximize the expected quadratic utility, defined as a weighted sum of the first and second moments of the rewards obtained through our policy. We subsequently demonstrate that the maximizer indeed qualifies as an MV-efficient policy. Previous studies that employed constrained optimization to address the MV trade-off have encountered computational challenges. However, our approach is more computationally efficient as it eliminates the need for gradient estimation of variance, a contributing factor to the double sampling issue observed in existing methodologies. Through experimentation, we validate the efficacy of our approach.
title Mean-Variance Efficient Reinforcement Learning with Applications to Dynamic Financial Investment
topic Machine Learning
url https://arxiv.org/abs/2010.01404