# A Regret Minimization Approach to Iterative Learning Control

arXiv: https://arxiv.org/abs/2102.13478 · HTML: https://mlsanity.com/paper/2102.13478/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 40 references that are in the map.
- First posted on arXiv 26 Feb 2021.

## Builds on (most cited first, 14 of 14)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [Online Control with Adversarial Disturbances](https://mlsanity.com/paper/1902.08721/) (2019)
- [Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator](https://mlsanity.com/paper/1805.09388/) (2018)
- [Improper Learning for Non-Stochastic Control](https://mlsanity.com/paper/2001.09254/) (2020)
- [Provable Guarantees for Gradient-Based Meta-Learning](https://mlsanity.com/paper/1902.10644/) (2019)
- [Online Linear Quadratic Control](https://mlsanity.com/paper/1806.07104/) (2018)
- [The Nonstochastic Control Problem](https://mlsanity.com/paper/1911.12178/) (2019)
- [Learning Model Predictive Control for iterative tasks. A Data-Driven Control Framework](https://mlsanity.com/paper/1609.01387/) (2016)
- [Logarithmic Regret for Online Control](https://mlsanity.com/paper/1909.05062/) (2019)
- [An Online Learning Approach to Model Predictive Control](https://mlsanity.com/paper/1902.08967/) (2019)
- [Making Non-Stochastic Control (Almost) as Easy as Stochastic](https://mlsanity.com/paper/2006.05910/) (2020)
- [Certainty Equivalence is Efficient for Linear Quadratic Control](https://mlsanity.com/paper/1902.07826/) (2019)
- [Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarking](https://mlsanity.com/paper/2102.09968/) (2021)

## Built on by (most cited first, 8 of 8)

- [Meta-Adaptive Nonlinear Control: Theory and Algorithms](https://mlsanity.com/paper/2106.06098/) (2021)
- [Online Control of Unknown Time-Varying Dynamical Systems](https://mlsanity.com/paper/2202.07890/) (2022)
- [Robust Online Control with Model Misspecification](https://mlsanity.com/paper/2107.07732/) (2021)
- [Online Control in Population Dynamics](https://mlsanity.com/paper/2406.01799/) (2024)
- [Online Nonstochastic Model-Free Reinforcement Learning](https://mlsanity.com/paper/2305.17552/) (2023)
- [On the Effectiveness of Iterative Learning Control](https://mlsanity.com/paper/2111.09434/) (2021)
- [Regret Analysis of Online Gradient Descent-based Iterative Learning Control with Model Mismatch](https://mlsanity.com/paper/2204.04722/) (2022)
- [Learning to Control under Time-Varying Environment](https://mlsanity.com/paper/2206.02507/) (2022)

## Abstract (arXiv)

We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics. In this setting, we propose a new performance metric, planning regret, which replaces the standard stochastic uncertainty assumptions with worst case regret. Based on recent advances in non-stochastic control, we design a new iterative algorithm for minimizing planning regret that is more robust to model mismatch and uncertainty. We provide theoretical and empirical evidence that the proposed algorithm outperforms existing methods on several benchmarks.