Tensor-Based Efficient Federated Reinforcement Learning for Cyber-Physical-Social Intelligence

Reinforcement Learning (RL) serves as a fundamental learning paradigm in the field of artificial intelligence, enabling decision-making policies through interactions with environments. However, traditional RL methods encounter challenges when dealing with large-scale or continuous state spaces due t...

Full description

Saved in:
Bibliographic Details
Main Authors: Xin Nie, Laurence T. Yang, Fulan Fan, Zecan Yang
Format: Article
Language:English
Published: Tsinghua University Press 2025-06-01
Series:Big Data Mining and Analytics
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/BDMA.2025.9020036
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849304042008739840
author Xin Nie
Laurence T. Yang
Fulan Fan
Zecan Yang
author_facet Xin Nie
Laurence T. Yang
Fulan Fan
Zecan Yang
author_sort Xin Nie
collection DOAJ
description Reinforcement Learning (RL) serves as a fundamental learning paradigm in the field of artificial intelligence, enabling decision-making policies through interactions with environments. However, traditional RL methods encounter challenges when dealing with large-scale or continuous state spaces due to the curse of dimensionality. Although Deep Reinforcement Learning (DRL) can handle complex environments, its lack of transparency and interpretability hinders its applicability due to the black box nature. Moreover, centralized data collection and processing methods pose privacy security risks. Federated learning offers a distributed approach that ensures privacy preservation while co-training models. However, existing federated reinforcement learning approaches have not adequately addressed communication and computation overhead issues. To address these challenges, this study proposes a tensor train decomposition-based federated reinforcement learning method that enhances efficiency and provides interpretability. By leveraging tensor to model state-action values and employing tensor decomposition techniques for dimensionality reduction, this method effectively reduces model parameters and communication overhead while maintaining strong interpretability, accelerates algorithm convergence speed. Experimental results validate the advantages of our proposed algorithm in terms of efficiency and reliability.
format Article
id doaj-art-a9f012c9eded454d896f0b4e0a859c72
institution Kabale University
issn 2096-0654
2097-406X
language English
publishDate 2025-06-01
publisher Tsinghua University Press
record_format Article
series Big Data Mining and Analytics
spelling doaj-art-a9f012c9eded454d896f0b4e0a859c722025-08-20T03:55:49ZengTsinghua University PressBig Data Mining and Analytics2096-06542097-406X2025-06-018486787910.26599/BDMA.2025.9020036Tensor-Based Efficient Federated Reinforcement Learning for Cyber-Physical-Social IntelligenceXin Nie0Laurence T. Yang1Fulan Fan2Zecan Yang3School of Computer and Artiffcial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China, and also with Department of Computer Science, St. Francis Xavier University, Antigonish, B2G 2W5, CanadaSchool of Education, South-Central Minzu University, Wuhan 430074, ChinaSchool of Computer and Artiffcial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaReinforcement Learning (RL) serves as a fundamental learning paradigm in the field of artificial intelligence, enabling decision-making policies through interactions with environments. However, traditional RL methods encounter challenges when dealing with large-scale or continuous state spaces due to the curse of dimensionality. Although Deep Reinforcement Learning (DRL) can handle complex environments, its lack of transparency and interpretability hinders its applicability due to the black box nature. Moreover, centralized data collection and processing methods pose privacy security risks. Federated learning offers a distributed approach that ensures privacy preservation while co-training models. However, existing federated reinforcement learning approaches have not adequately addressed communication and computation overhead issues. To address these challenges, this study proposes a tensor train decomposition-based federated reinforcement learning method that enhances efficiency and provides interpretability. By leveraging tensor to model state-action values and employing tensor decomposition techniques for dimensionality reduction, this method effectively reduces model parameters and communication overhead while maintaining strong interpretability, accelerates algorithm convergence speed. Experimental results validate the advantages of our proposed algorithm in terms of efficiency and reliability.https://www.sciopen.com/article/10.26599/BDMA.2025.9020036cyber-physical-social intelligence (cpsi)federated reinforcement learning (frl)tensor train decomposition
spellingShingle Xin Nie
Laurence T. Yang
Fulan Fan
Zecan Yang
Tensor-Based Efficient Federated Reinforcement Learning for Cyber-Physical-Social Intelligence
Big Data Mining and Analytics
cyber-physical-social intelligence (cpsi)
federated reinforcement learning (frl)
tensor train decomposition
title Tensor-Based Efficient Federated Reinforcement Learning for Cyber-Physical-Social Intelligence
title_full Tensor-Based Efficient Federated Reinforcement Learning for Cyber-Physical-Social Intelligence
title_fullStr Tensor-Based Efficient Federated Reinforcement Learning for Cyber-Physical-Social Intelligence
title_full_unstemmed Tensor-Based Efficient Federated Reinforcement Learning for Cyber-Physical-Social Intelligence
title_short Tensor-Based Efficient Federated Reinforcement Learning for Cyber-Physical-Social Intelligence
title_sort tensor based efficient federated reinforcement learning for cyber physical social intelligence
topic cyber-physical-social intelligence (cpsi)
federated reinforcement learning (frl)
tensor train decomposition
url https://www.sciopen.com/article/10.26599/BDMA.2025.9020036
work_keys_str_mv AT xinnie tensorbasedefficientfederatedreinforcementlearningforcyberphysicalsocialintelligence
AT laurencetyang tensorbasedefficientfederatedreinforcementlearningforcyberphysicalsocialintelligence
AT fulanfan tensorbasedefficientfederatedreinforcementlearningforcyberphysicalsocialintelligence
AT zecanyang tensorbasedefficientfederatedreinforcementlearningforcyberphysicalsocialintelligence