Learning to Focus: CSI-Free Hierarchical MARL for Reconfigurable Reflectors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Le, Hieu, Ibrahim, Mostafa, Bedir, Oguz, Tao, Jian, Ekin, Sabit
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908959477071872
author Le, Hieu
Ibrahim, Mostafa
Bedir, Oguz
Tao, Jian
Ekin, Sabit
author_facet Le, Hieu
Ibrahim, Mostafa
Bedir, Oguz
Tao, Jian
Ekin, Sabit
contents Reconfigurable Intelligent Surfaces (RIS) has a potential to engineer smart radio environments for next-generation millimeter-wave (mmWave) networks. However, the prohibitive computational overhead of Channel State Information (CSI) estimation and the dimensionality explosion inherent in centralized optimization severely hinder practical large-scale deployments. To overcome these bottlenecks, we introduce a ``CSI-free" paradigm powered by a Hierarchical Multi-Agent Reinforcement Learning (HMARL) architecture to control mechanically reconfigurable reflective surfaces. By substituting pilot-based channel estimation with accessible user localization data, our framework leverages spatial intelligence for macro-scale wave propagation management. The control problem is decomposed into a two-tier neural architecture: a high-level controller executes temporally extended, discrete user-to-reflector allocations, while low-level controllers autonomously optimize continuous focal points utilizing Multi-Agent Proximal Policy Optimization (MAPPO) under a Centralized Training with Decentralized Execution (CTDE) scheme. Comprehensive deterministic ray-tracing evaluations demonstrate that this hierarchical framework achieves massive RSSI improvements of up to 7.79 dB over centralized baselines. Furthermore, the system exhibits robust multi-user scalability and maintains highly resilient beam-focusing performance under practical sub-meter localization tracking errors. By eliminating CSI overhead while maintaining high-fidelity signal redirection, this work establishes a scalable and cost-effective blueprint for intelligent wireless environments.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05165
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning to Focus: CSI-Free Hierarchical MARL for Reconfigurable Reflectors
Le, Hieu
Ibrahim, Mostafa
Bedir, Oguz
Tao, Jian
Ekin, Sabit
Artificial Intelligence
Signal Processing
Reconfigurable Intelligent Surfaces (RIS) has a potential to engineer smart radio environments for next-generation millimeter-wave (mmWave) networks. However, the prohibitive computational overhead of Channel State Information (CSI) estimation and the dimensionality explosion inherent in centralized optimization severely hinder practical large-scale deployments. To overcome these bottlenecks, we introduce a ``CSI-free" paradigm powered by a Hierarchical Multi-Agent Reinforcement Learning (HMARL) architecture to control mechanically reconfigurable reflective surfaces. By substituting pilot-based channel estimation with accessible user localization data, our framework leverages spatial intelligence for macro-scale wave propagation management. The control problem is decomposed into a two-tier neural architecture: a high-level controller executes temporally extended, discrete user-to-reflector allocations, while low-level controllers autonomously optimize continuous focal points utilizing Multi-Agent Proximal Policy Optimization (MAPPO) under a Centralized Training with Decentralized Execution (CTDE) scheme. Comprehensive deterministic ray-tracing evaluations demonstrate that this hierarchical framework achieves massive RSSI improvements of up to 7.79 dB over centralized baselines. Furthermore, the system exhibits robust multi-user scalability and maintains highly resilient beam-focusing performance under practical sub-meter localization tracking errors. By eliminating CSI overhead while maintaining high-fidelity signal redirection, this work establishes a scalable and cost-effective blueprint for intelligent wireless environments.
title Learning to Focus: CSI-Free Hierarchical MARL for Reconfigurable Reflectors
topic Artificial Intelligence
Signal Processing
url https://arxiv.org/abs/2604.05165