# Decentralized Spatial Reuse Optimization in Wi-Fi: An Internal Regret Minimization Approach

arXiv: https://arxiv.org/abs/2602.08456 · HTML: https://mlsanity.com/paper/2602.08456/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 10 of 10)

- [Potential and Pitfalls of Multi-Armed Bandits for Decentralized Spatial Reuse in WLANs](https://mlsanity.com/paper/1805.11083/) (2018)
- [Komondor: a Wireless Network Simulator for Next-Generation High-Density WLANs](https://mlsanity.com/paper/1811.12397/) (2018)
- [Implications of Decentralized Q-learning Resource Allocation in Wireless Networks](https://mlsanity.com/paper/1705.10508/) (2017)
- [Collaborative Spatial Reuse in Wireless Networks via Selfish Multi-Armed Bandits](https://mlsanity.com/paper/1710.11403/) (2017)
- [Spatial Reuse in IEEE 802.11ax WLANs](https://mlsanity.com/paper/1907.04141/) (2019)
- [Channel Selection for Network-assisted D2D Communication via No-Regret Bandit Learning with Calibrated Forecasting](https://mlsanity.com/paper/1404.7061/) (2014)
- [Wi-Fi: Twenty-Five Years and Counting](https://mlsanity.com/paper/2507.09613/) (2025)
- [On the Latency of IEEE 802.11ax WLANs with Parameterized Spatial Reuse](https://mlsanity.com/paper/2008.07482/) (2020)
- [Cooperate or not Cooperate: Transfer Learning with Multi-Armed Bandit for Spatial Reuse in Wi-Fi](https://mlsanity.com/paper/2211.15741/) (2022)
- [Coordinated Multi-Armed Bandits for Improved Spatial Reuse in Wi-Fi](https://mlsanity.com/paper/2412.03076/) (2024)

## Abstract (arXiv)

Spatial Reuse (SR) is a cost-effective technique for improving spectral efficiency in dense IEEE 802.11 deployments by enabling simultaneous transmissions. However, the decentralized optimization of SR parameters -- transmission power and Carrier Sensing Threshold (CST) -- across different Basic Service Sets (BSSs) is challenging due to the lack of global state information. In addition, the concurrent operation of multiple agents creates a highly non-stationary environment, often resulting in suboptimal global configurations (e.g., using the maximum possible transmission power by default). To overcome these limitations, this paper introduces a decentralized learning algorithm based on regret-matching, grounded in internal regret minimization. Unlike standard decentralized ``selfish'' approaches that often converge to inefficient Nash Equilibria (NE), internal regret minimization guides competing agents toward Correlated Equilibria (CE), effectively mimicking coordination without explicit communication. Through simulation results, we showcase the superiority of our proposed approach and its ability to reach near-optimal global performance. These results confirm the not-yet-unleashed potential of scalable decentralized solutions and question the need for the heavy signaling overheads and architectural complexity associated with emerging centralized solutions like Multi-Access Point Coordination (MAPC).