Federated Reinforcement Learning (FRL) offers a promising solution to various practical challenges in resource allocation for vehicle-to-everything (V2X) networks. However, the data discrepancy among individual agents can significantly degrade the performance of FRL-based algorithms. To address this limitation, we exploit the node-wise invariance property of ReLU-activated neural networks, with the aim of reducing data discrepancy to improve learning performance. Based on this property, we introduce a backward rescale-invariant operation to develop a rescale-invariant FRL algorithm. Simulation results demonstrate that the proposed algorithm notably enhances both convergence speed and convergent performance.
@article{arxiv.2405.01961,
title = {Rescale-Invariant Federated Reinforcement Learning for Resource Allocation in V2X Networks},
author = {Kaidi Xu and Shenglong Zhou and Geoffrey Ye Li},
journal= {arXiv preprint arXiv:2405.01961},
year = {2024}
}