# Learn to Compress CSI and Allocate Resources in Vehicular Networks

arXiv: https://arxiv.org/abs/1908.04685 · HTML: https://mlsanity.com/paper/1908.04685/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2019.

## Built on by (most cited first, 4 of 4)

- [Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey](https://mlsanity.com/paper/2110.13484/) (2021)
- [Optimizing the Long-Term Average Reward for Continuing MDPs: A Technical Report](https://mlsanity.com/paper/2104.06139/) (2021)
- [Small-Scale-Fading-Aware Resource Allocation in Wireless Federated Learning](https://mlsanity.com/paper/2505.03533/) (2025)
- [SCAR: State-Space Compression for Scalable AI-Based Network Management of Vehicular Services](https://mlsanity.com/paper/2508.06243/) (2025)

## Abstract (arXiv)

Resource allocation has a direct and profound impact on the performance of vehicle-to-everything (V2X) networks. In this paper, we develop a hybrid architecture consisting of centralized decision making and distributed resource sharing (the C-Decision scheme) to maximize the long-term sum rate of all vehicles. To reduce the network signaling overhead, each vehicle uses a deep neural network to compress its observed information that is thereafter fed back to the centralized decision making unit. The centralized decision unit employs a deep Q-network to allocate resources and then sends the decision results to all vehicles. We further adopt a quantization layer for each vehicle that learns to quantize the continuous feedback. In addition, we devise a mechanism to balance the transmission of vehicle-to-vehicle (V2V) links and vehicle-to-infrastructure (V2I) links. To further facilitate distributed spectrum sharing, we also propose a distributed decision making and spectrum sharing architecture (the D-Decision scheme) for each V2V link. Through extensive simulation results, we demonstrate that the proposed C-Decision and D-Decision schemes can both achieve near-optimal performance and are robust to feedback interval variations, input noise, and feedback noise.