# Meta-Learning Guarantees for Online Receding Horizon Learning Control

arXiv: https://arxiv.org/abs/2010.11327 · HTML: https://mlsanity.com/paper/2010.11327/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

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

- [Meta-Learning of Neural State-Space Models Using Data From Similar Systems](https://mlsanity.com/paper/2211.07768/) (2022)
- [Meta-Learning for Physically-Constrained Neural System Identification](https://mlsanity.com/paper/2501.06167/) (2025)

## Abstract (arXiv)

In this paper we provide provable regret guarantees for an online meta-learning receding horizon control algorithm in an iterative control setting. We consider the setting where, in each iteration the system to be controlled is a linear deterministic system that is different and unknown, the cost for the controller in an iteration is a general additive cost function and there are affine control input constraints. By analysing conditions under which sub-linear regret is achievable, we prove that the meta-learning online receding horizon controller achieves an average of the dynamic regret for the controller cost that is tildeO((1+1/√N)T3/4) with the number of iterations N. Thus, we show that the worst regret for learning within an iteration improves with experience of more iterations, with guarantee on rate of improvement.