Saved in:
Bibliographic Details
Main Authors: Wu, Liangshun, Chen, Wen, Zhang, Shunqing, Wang, Yajun, Wang, Kunlun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.12892
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909906232147968
author Wu, Liangshun
Chen, Wen
Zhang, Shunqing
Wang, Yajun
Wang, Kunlun
author_facet Wu, Liangshun
Chen, Wen
Zhang, Shunqing
Wang, Yajun
Wang, Kunlun
contents In post-disaster space-air-ground integrated networks (SAGINs), terrestrial infrastructure is often impaired, and unmanned aerial vehicles (UAVs) must rapidly restore connectivity for mission-critical ground terminals in cluttered non-line-of-sight (NLoS) urban environments. To enhance coverage, UAVs employ movable antennas (MAs), while reconfigurable intelligent surfaces (RISs) on surviving high-rises redirect signals. The key challenge is communication-limited partial observability, leaving each UAV with a narrow, fast-changing neighborhood view that destabilizes value estimation. Existing multi-agent reinforcement learning (MARL) approaches are inadequate--non-communication methods rely on unavailable global critics, heuristic sharing is brittle and redundant, and learnable protocols (e.g., CommNet, DIAL) lose per-neighbor structure and aggravate non-stationarity under tight bandwidth. To address partial observability, we propose a spatiotemporal A2C where each UAV transmits prior-decision messages with local state, a compact policy fingerprint, and a recurrent belief, encoded per neighbor and concatenated. A spatial discount shapes value targets to emphasize local interactions, while analysis under one-hop-per-slot latency explains stable training with delayed views. Experimental results show our policy outperforms IA2C, ConseNet, FPrint, DIAL, and CommNet--achieving faster convergence, higher asymptotic reward, reduced Temporal-Difference(TD)/advantage errors, and a better communication throughput-energy trade-off.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12892
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Green Emergency Communications in RIS- and MA-Assisted Multi-UAV SAGINs: A Partially Observable Reinforcement Learning Approach
Wu, Liangshun
Chen, Wen
Zhang, Shunqing
Wang, Yajun
Wang, Kunlun
Systems and Control
In post-disaster space-air-ground integrated networks (SAGINs), terrestrial infrastructure is often impaired, and unmanned aerial vehicles (UAVs) must rapidly restore connectivity for mission-critical ground terminals in cluttered non-line-of-sight (NLoS) urban environments. To enhance coverage, UAVs employ movable antennas (MAs), while reconfigurable intelligent surfaces (RISs) on surviving high-rises redirect signals. The key challenge is communication-limited partial observability, leaving each UAV with a narrow, fast-changing neighborhood view that destabilizes value estimation. Existing multi-agent reinforcement learning (MARL) approaches are inadequate--non-communication methods rely on unavailable global critics, heuristic sharing is brittle and redundant, and learnable protocols (e.g., CommNet, DIAL) lose per-neighbor structure and aggravate non-stationarity under tight bandwidth. To address partial observability, we propose a spatiotemporal A2C where each UAV transmits prior-decision messages with local state, a compact policy fingerprint, and a recurrent belief, encoded per neighbor and concatenated. A spatial discount shapes value targets to emphasize local interactions, while analysis under one-hop-per-slot latency explains stable training with delayed views. Experimental results show our policy outperforms IA2C, ConseNet, FPrint, DIAL, and CommNet--achieving faster convergence, higher asymptotic reward, reduced Temporal-Difference(TD)/advantage errors, and a better communication throughput-energy trade-off.
title Green Emergency Communications in RIS- and MA-Assisted Multi-UAV SAGINs: A Partially Observable Reinforcement Learning Approach
topic Systems and Control
url https://arxiv.org/abs/2511.12892