# DRL-Based Beam Positioning for LEO Satellite Constellations with Weighted Least Squares

arXiv: https://arxiv.org/abs/2511.08852 · HTML: https://mlsanity.com/paper/2511.08852/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 12 Nov 2025.

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

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Handover Protocol Learning for LEO Satellite Networks: Access Delay and Collision Minimization](https://mlsanity.com/paper/2310.20215/) (2023)
- [Cooperative Beam Hopping for Accurate Positioning in Ultra-Dense LEO Satellite Networks](https://mlsanity.com/paper/2103.16766/) (2021)
- [Integrated 6G TN and NTN Localization: Challenges, Opportunities, and Advancements](https://mlsanity.com/paper/2501.13488/) (2025)
- [A Novel Satellite Selection Algorithm Using LSTM Neural Networks For Single-epoch Localization](https://mlsanity.com/paper/2306.05717/) (2023)
- [Flexible Robust Beamforming for Multibeam Satellite Downlink using Reinforcement Learning](https://mlsanity.com/paper/2402.16563/) (2024)
- [Joint Beam Scheduling and Beamforming Design for Cooperative Positioning in Multi-beam LEO Satellite Networks](https://mlsanity.com/paper/2404.01148/) (2024)
- [Beam Management in Low Earth Orbit Satellite Networks with Random Traffic Arrival and Time-varying Topology](https://mlsanity.com/paper/2404.08959/) (2024)

## Built on by (most cited first, 2 of 2)

- [Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks](https://mlsanity.com/paper/2605.02413/) (2026)
- [Dueling DDQN-Based Adaptive Multi-Objective Handover Optimization for LEO Satellite Networks](https://mlsanity.com/paper/2605.02416/) (2026)

## Abstract (arXiv)

This paper investigates a lightweight deep reinforcement learning (DRL)-assisted weighting framework for CSI-free multi-satellite positioning in LEO constellations, where each visible satellite provides one serving beam (one pilot response) per epoch. A discrete-action Deep Q-Network (DQN) learns satellite weights directly from received pilot measurements and geometric features, while an augmented weighted least squares (WLS) estimator provides physics-consistent localization and jointly estimates the receiver clock bias. The proposed hybrid design targets an accuracy-runtime trade-off rather than absolute supervised optimality. In a representative 2-D setting with 10 visible satellites, the proposed approach achieves sub-meter accuracy (0.395m RMSE) with low computational overhead, supporting practical deployment for resource-constrained LEO payloads.