Saved in:
Bibliographic Details
Main Authors: Nowosadko, Konrad, Ruggeri, Franco, Terra, Ahmad
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.14925
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916956254240768
author Nowosadko, Konrad
Ruggeri, Franco
Terra, Ahmad
author_facet Nowosadko, Konrad
Ruggeri, Franco
Terra, Ahmad
contents Reinforcement Learning (RL) methods that incorporate deep neural networks (DNN), though powerful, often lack transparency. Their black-box characteristic hinders interpretability and reduces trustworthiness, particularly in critical domains. To address this challenge in RL tasks, we propose a solution based on Self-Explaining Neural Networks (SENNs) along with explanation extraction methods to enhance interpretability while maintaining predictive accuracy. Our approach targets low-dimensionality problems to generate robust local and global explanations of the model's behaviour. We evaluate the proposed method on the resource allocation problem in mobile networks, demonstrating that SENNs can constitute interpretable solutions with competitive performance. This work highlights the potential of SENNs to improve transparency and trust in AI-driven decision-making for low-dimensional tasks. Our approach strong performance on par with the existing state-of-the-art methods, while providing robust explanations.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14925
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Self-Explaining Reinforcement Learning for Mobile Network Resource Allocation
Nowosadko, Konrad
Ruggeri, Franco
Terra, Ahmad
Machine Learning
Networking and Internet Architecture
Reinforcement Learning (RL) methods that incorporate deep neural networks (DNN), though powerful, often lack transparency. Their black-box characteristic hinders interpretability and reduces trustworthiness, particularly in critical domains. To address this challenge in RL tasks, we propose a solution based on Self-Explaining Neural Networks (SENNs) along with explanation extraction methods to enhance interpretability while maintaining predictive accuracy. Our approach targets low-dimensionality problems to generate robust local and global explanations of the model's behaviour. We evaluate the proposed method on the resource allocation problem in mobile networks, demonstrating that SENNs can constitute interpretable solutions with competitive performance. This work highlights the potential of SENNs to improve transparency and trust in AI-driven decision-making for low-dimensional tasks. Our approach strong performance on par with the existing state-of-the-art methods, while providing robust explanations.
title Self-Explaining Reinforcement Learning for Mobile Network Resource Allocation
topic Machine Learning
Networking and Internet Architecture
url https://arxiv.org/abs/2509.14925