A Tensor Low-Rank Approximation for Value Functions in Multi-Task Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rozada, Sergio, Paternain, Santiago, Bazerque, Juan Andres, Marques, Antonio G.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913655544610816
author Rozada, Sergio
Paternain, Santiago
Bazerque, Juan Andres
Marques, Antonio G.
author_facet Rozada, Sergio
Paternain, Santiago
Bazerque, Juan Andres
Marques, Antonio G.
contents In pursuit of reinforcement learning systems that could train in physical environments, we investigate multi-task approaches as a means to alleviate the need for massive data acquisition. In a tabular scenario where the Q-functions are collected across tasks, we model our learning problem as optimizing a higher order tensor structure. Recognizing that close-related tasks may require similar actions, our proposed method imposes a low-rank condition on this aggregated Q-tensor. The rationale behind this approach to multi-task learning is that the low-rank structure enforces the notion of similarity, without the need to explicitly prescribe which tasks are similar, but inferring this information from a reduced amount of data simultaneously with the stochastic optimization of the Q-tensor. The efficiency of our low-rank tensor approach to multi-task learning is demonstrated in two numerical experiments, first in a benchmark environment formed by a collection of inverted pendulums, and then into a practical scenario involving multiple wireless communication devices.
format Preprint
id arxiv_https___arxiv_org_abs_2501_10529
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Tensor Low-Rank Approximation for Value Functions in Multi-Task Reinforcement Learning
Rozada, Sergio
Paternain, Santiago
Bazerque, Juan Andres
Marques, Antonio G.
Machine Learning
In pursuit of reinforcement learning systems that could train in physical environments, we investigate multi-task approaches as a means to alleviate the need for massive data acquisition. In a tabular scenario where the Q-functions are collected across tasks, we model our learning problem as optimizing a higher order tensor structure. Recognizing that close-related tasks may require similar actions, our proposed method imposes a low-rank condition on this aggregated Q-tensor. The rationale behind this approach to multi-task learning is that the low-rank structure enforces the notion of similarity, without the need to explicitly prescribe which tasks are similar, but inferring this information from a reduced amount of data simultaneously with the stochastic optimization of the Q-tensor. The efficiency of our low-rank tensor approach to multi-task learning is demonstrated in two numerical experiments, first in a benchmark environment formed by a collection of inverted pendulums, and then into a practical scenario involving multiple wireless communication devices.
title A Tensor Low-Rank Approximation for Value Functions in Multi-Task Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2501.10529