# Risk-Based Optimization of Virtual Reality over Terahertz Reconfigurable Intelligent Surfaces

arXiv: https://arxiv.org/abs/2002.09052 · HTML: https://mlsanity.com/paper/2002.09052/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2020.

## Built on by (most cited first, 3 of 3)

- [Meta-Reinforcement Learning for Reliable Communication in THz/VLC Wireless VR Networks](https://mlsanity.com/paper/2102.12277/) (2021)
- [Ultra-Reliable Indoor Millimeter Wave Communications using Multiple Artificial Intelligence-Powered Intelligent Surfaces](https://mlsanity.com/paper/2104.00075/) (2021)
- [A Fast Task Offloading Optimization Framework for IRS-Assisted Multi-Access Edge Computing System](https://mlsanity.com/paper/2307.08474/) (2023)

## Abstract (arXiv)

In this paper, the problem of associating reconfigurable intelligent surfaces (RISs) to virtual reality (VR) users is studied for a wireless VR network. In particular, this problem is considered within a cellular network that employs terahertz (THz) operated RISs acting as base stations. To provide a seamless VR experience, high data rates and reliable low latency need to be continuously guaranteed. To address these challenges, a novel risk-based framework based on the entropic value-at-risk is proposed for rate optimization and reliability performance. Furthermore, a Lyapunov optimization technique is used to reformulate the problem as a linear weighted function, while ensuring that higher order statistics of the queue length are maintained under a threshold. To address this problem, given the stochastic nature of the channel, a policy-based reinforcement learning (RL) algorithm is proposed. Since the state space is extremely large, the policy is learned through a deep-RL algorithm. In particular, a recurrent neural network (RNN) RL framework is proposed to capture the dynamic channel behavior and improve the speed of conventional RL policy-search algorithms. Simulation results demonstrate that the maximal queue length resulting from the proposed approach is only within 1% of the optimal solution. The results show a high accuracy and fast convergence for the RNN with a validation accuracy of 91.92%.