# Robust exploration in linear quadratic reinforcement learning

arXiv: https://arxiv.org/abs/1906.01584 · HTML: https://mlsanity.com/paper/1906.01584/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2019.

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

- [Differentiable Robust LQR Layers](https://mlsanity.com/paper/2106.05535/) (2021)
- [Thompson Sampling-Based Learning and Control for Unknown Dynamic Systems](https://mlsanity.com/paper/2506.22186/) (2025)

## Abstract (arXiv)

This paper concerns the problem of learning control policies for an unknown linear dynamical system to minimize a quadratic cost function. We present a method, based on convex optimization, that accomplishes this task robustly: i.e., we minimize the worst-case cost, accounting for system uncertainty given the observed data. The method balances exploitation and exploration, exciting the system in such a way so as to reduce uncertainty in the model parameters to which the worst-case cost is most sensitive. Numerical simulations and application to a hardware-in-the-loop servo-mechanism demonstrate the approach, with appreciable performance and robustness gains over alternative methods observed in both.