# Fair Dynamic Spectrum Access via Fully Decentralized Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2503.24296 · HTML: https://mlsanity.com/paper/2503.24296/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 9 of 9)

- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [Implicit Quantile Networks for Distributional Reinforcement Learning](https://mlsanity.com/paper/1806.06923/) (2018)
- [Applications of Deep Reinforcement Learning in Communications and Networking: A Survey](https://mlsanity.com/paper/1810.07862/) (2018)
- [InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling](https://mlsanity.com/paper/2402.09345/) (2024)
- [Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity](https://mlsanity.com/paper/2210.09579/) (2022)
- [Deep-Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks](https://mlsanity.com/paper/1712.00162/) (2017)
- [Deep Reinforcement Learning for Simultaneous Sensing and Channel Access in Cognitive Networks](https://mlsanity.com/paper/2110.14541/) (2021)
- [Dynamic Channel Access and Power Control in Wireless Interference Networks via Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/2112.14709/) (2021)
- [Dynamic Multichannel Access via Multi-agent Reinforcement Learning: Throughput and Fairness Guarantees](https://mlsanity.com/paper/2105.04077/) (2021)

## Abstract (arXiv)

We consider a decentralized wireless network with several source-destination pairs sharing a limited number of orthogonal frequency bands. Sources learn to adapt their transmissions (specifically, their band selection strategy) over time, in a decentralized manner, without sharing information with each other. Sources can only observe the outcome of their own transmissions (i.e., success or collision), having no prior knowledge of the network size or of the transmission strategy of other sources. The goal of each source is to maximize their own throughput while striving for network-wide fairness. We propose a novel fully decentralized Reinforcement Learning (RL)-based solution that achieves fairness without coordination. The proposed Fair Share RL (FSRL) solution combines: (i) state augmentation with a semi-adaptive time reference; (ii) an architecture that leverages risk control and time difference likelihood; and (iii) a fairness-driven reward structure. We evaluate FSRL in more than 50 network settings with different number of agents, different amounts of available spectrum, in the presence of jammers, and in an ad-hoc setting. Simulation results suggest that, when we compare FSRL with a common baseline RL algorithm from the literature, FSRL can be up to 89.0% fairer (as measured by Jain's fairness index) in stringent settings with several sources and a single frequency band, and 48.1% fairer on average.