Foundation Model-Aided Hierarchical Deep Reinforcement Learning for Blockage-Aware Link in RIS-Assisted Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912893452156928 |
|---|---|
| author | Ghassemi, Mohammad Zhang, Han Afana, Ali Sediq, Akram Bin Erol-Kantarci, Melike |
| author_facet | Ghassemi, Mohammad Zhang, Han Afana, Ali Sediq, Akram Bin Erol-Kantarci, Melike |
| contents | Reconfigurable intelligent surface (RIS) technology has the potential to significantly enhance the spectral efficiency (SE) of 6G wireless networks. However, practical deployment remains constrained by challenges in accurate channel estimation and control optimization under dynamic conditions. This paper presents a foundation model-aided hierarchical deep reinforcement learning (FM-HDRL) framework designed for joint beamforming and phase-shift optimization in RIS-assisted wireless networks. To implement this, we first fine-tune a pre-trained large wireless model (LWM) to translate raw channel data into low-dimensional, context-aware channel state information (CSI) embeddings. Next, these embeddings are combined with user location information and blockage status to select the optimal communication path. The resulting features are then fed into an HDRL model, assumed to be implemented at a centralized controller, which jointly optimizes the base station (BS) beamforming vectors and the RIS phase-shift configurations to maximize SE. Simulation results demonstrate that the proposed FM-HDRL framework consistently outperforms baseline methods in terms of convergence speed, spectral efficiency, and scalability. According to the simulation results, our proposed method improves 7.82% SE compared to the FM-aided deep reinforcement learning (FM-DRL) approach and a substantial enhancement of about 48.66% relative to the beam sweeping approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09157 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Foundation Model-Aided Hierarchical Deep Reinforcement Learning for Blockage-Aware Link in RIS-Assisted Networks Ghassemi, Mohammad Zhang, Han Afana, Ali Sediq, Akram Bin Erol-Kantarci, Melike Signal Processing Reconfigurable intelligent surface (RIS) technology has the potential to significantly enhance the spectral efficiency (SE) of 6G wireless networks. However, practical deployment remains constrained by challenges in accurate channel estimation and control optimization under dynamic conditions. This paper presents a foundation model-aided hierarchical deep reinforcement learning (FM-HDRL) framework designed for joint beamforming and phase-shift optimization in RIS-assisted wireless networks. To implement this, we first fine-tune a pre-trained large wireless model (LWM) to translate raw channel data into low-dimensional, context-aware channel state information (CSI) embeddings. Next, these embeddings are combined with user location information and blockage status to select the optimal communication path. The resulting features are then fed into an HDRL model, assumed to be implemented at a centralized controller, which jointly optimizes the base station (BS) beamforming vectors and the RIS phase-shift configurations to maximize SE. Simulation results demonstrate that the proposed FM-HDRL framework consistently outperforms baseline methods in terms of convergence speed, spectral efficiency, and scalability. According to the simulation results, our proposed method improves 7.82% SE compared to the FM-aided deep reinforcement learning (FM-DRL) approach and a substantial enhancement of about 48.66% relative to the beam sweeping approach. |
| title | Foundation Model-Aided Hierarchical Deep Reinforcement Learning for Blockage-Aware Link in RIS-Assisted Networks |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2602.09157 |