Causally-Aware Reinforcement Learning for Joint Communication and Sensing

The next-generation wireless network, 6G and beyond, envisions to integrate communication and sensing to overcome interference, improve spectrum efficiency, and reduce hardware and power consumption. Massive Multiple-Input Multiple Output (mMIMO)-based Joint Communication and Sensing (JCAS) systems...

Full description

Saved in:
Bibliographic Details
Main Authors: Anik Roy, Serene Banerjee, Jishnu Sadasivan, Arnab Sarkar, Soumyajit Dey
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Transactions on Machine Learning in Communications and Networking
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10971373/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850281377743765504
author Anik Roy
Serene Banerjee
Jishnu Sadasivan
Arnab Sarkar
Soumyajit Dey
author_facet Anik Roy
Serene Banerjee
Jishnu Sadasivan
Arnab Sarkar
Soumyajit Dey
author_sort Anik Roy
collection DOAJ
description The next-generation wireless network, 6G and beyond, envisions to integrate communication and sensing to overcome interference, improve spectrum efficiency, and reduce hardware and power consumption. Massive Multiple-Input Multiple Output (mMIMO)-based Joint Communication and Sensing (JCAS) systems realize this integration for 6G applications such as autonomous driving, as it requires accurate environmental sensing and time-critical communication with neighbouring vehicles. Reinforcement Learning (RL) is used for mMIMO antenna beamforming in the existing literature. However, the huge search space for actions associated with antenna beamforming causes the learning process for the RL agent to be inefficient due to high beam training overhead. The learning process does not consider the causal relationship between action space and the reward, and gives all actions equal importance. In this work, we explore a causally-aware RL agent which can intervene and discover causal relationships for mMIMO-based JCAS environments, during the training phase. We use a state dependent action dimension selection strategy to realize causal discovery for RL-based JCAS. Evaluation of the causally-aware RL framework in different JCAS scenarios shows the benefit of our proposed solution over baseline methods in terms of the higher reward. We have shown that in the presence of interfering users and sensing signal clutters, our proposed solution achieves 30% higher data rate in comparison to the communication-only state-of-the-art beam pattern learning method while maintaining sensing performance.
format Article
id doaj-art-aa40b40ed3b34ea9b54176fd0d1341fb
institution OA Journals
issn 2831-316X
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Machine Learning in Communications and Networking
spelling doaj-art-aa40b40ed3b34ea9b54176fd0d1341fb2025-08-20T01:48:20ZengIEEEIEEE Transactions on Machine Learning in Communications and Networking2831-316X2025-01-01355256710.1109/TMLCN.2025.356255710971373Causally-Aware Reinforcement Learning for Joint Communication and SensingAnik Roy0https://orcid.org/0009-0003-3942-1830Serene Banerjee1https://orcid.org/0000-0002-5579-4819Jishnu Sadasivan2https://orcid.org/0000-0003-3990-8254Arnab Sarkar3https://orcid.org/0000-0002-5930-2180Soumyajit Dey4https://orcid.org/0000-0001-9329-6389Indian Institute of Technology Kharagpur, Kharagpur, IndiaEricsson Research, Bengaluru, IndiaEricsson Research, Bengaluru, IndiaIndian Institute of Technology Kharagpur, Kharagpur, IndiaIndian Institute of Technology Kharagpur, Kharagpur, IndiaThe next-generation wireless network, 6G and beyond, envisions to integrate communication and sensing to overcome interference, improve spectrum efficiency, and reduce hardware and power consumption. Massive Multiple-Input Multiple Output (mMIMO)-based Joint Communication and Sensing (JCAS) systems realize this integration for 6G applications such as autonomous driving, as it requires accurate environmental sensing and time-critical communication with neighbouring vehicles. Reinforcement Learning (RL) is used for mMIMO antenna beamforming in the existing literature. However, the huge search space for actions associated with antenna beamforming causes the learning process for the RL agent to be inefficient due to high beam training overhead. The learning process does not consider the causal relationship between action space and the reward, and gives all actions equal importance. In this work, we explore a causally-aware RL agent which can intervene and discover causal relationships for mMIMO-based JCAS environments, during the training phase. We use a state dependent action dimension selection strategy to realize causal discovery for RL-based JCAS. Evaluation of the causally-aware RL framework in different JCAS scenarios shows the benefit of our proposed solution over baseline methods in terms of the higher reward. We have shown that in the presence of interfering users and sensing signal clutters, our proposed solution achieves 30% higher data rate in comparison to the communication-only state-of-the-art beam pattern learning method while maintaining sensing performance.https://ieeexplore.ieee.org/document/10971373/Causal discoveryreinforcement learningantenna beamformingjoint communicationsensing
spellingShingle Anik Roy
Serene Banerjee
Jishnu Sadasivan
Arnab Sarkar
Soumyajit Dey
Causally-Aware Reinforcement Learning for Joint Communication and Sensing
IEEE Transactions on Machine Learning in Communications and Networking
Causal discovery
reinforcement learning
antenna beamforming
joint communication
sensing
title Causally-Aware Reinforcement Learning for Joint Communication and Sensing
title_full Causally-Aware Reinforcement Learning for Joint Communication and Sensing
title_fullStr Causally-Aware Reinforcement Learning for Joint Communication and Sensing
title_full_unstemmed Causally-Aware Reinforcement Learning for Joint Communication and Sensing
title_short Causally-Aware Reinforcement Learning for Joint Communication and Sensing
title_sort causally aware reinforcement learning for joint communication and sensing
topic Causal discovery
reinforcement learning
antenna beamforming
joint communication
sensing
url https://ieeexplore.ieee.org/document/10971373/
work_keys_str_mv AT anikroy causallyawarereinforcementlearningforjointcommunicationandsensing
AT serenebanerjee causallyawarereinforcementlearningforjointcommunicationandsensing
AT jishnusadasivan causallyawarereinforcementlearningforjointcommunicationandsensing
AT arnabsarkar causallyawarereinforcementlearningforjointcommunicationandsensing
AT soumyajitdey causallyawarereinforcementlearningforjointcommunicationandsensing