mlsanityData to 14 Oct 2026

Adaptive Online Non-stochastic Control

arXiv 2310.02261 ↗First posted 2 Oct 2023math.OC cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of Non-stochastic Control (NSC) with the aim of obtaining algorithms whose policy regret is proportional to the difficulty of the controlled environment. Namely, we tailor the Follow The Regularized Leader (FTRL) framework to dynamical systems by using regularizers that are proportional to the actual witnessed costs. The main challenge arises from using the proposed adaptive regularizers in the presence of a state, or equivalently, a memory, which couples the effect of the online decisions and requires new tools for bounding the regret. Via new analysis techniques for NSC and FTRL integration, we obtain novel disturbance action controllers (DAC) with sub-linear data adaptive policy regret bounds that shrink when the trajectory of costs has small gradients, while staying sub-linear even in the worst case.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 29 of its 41 references that are in the map. First posted on arXiv 2 Oct 2023.

Builds on

29 of 41 references.

References · 29

  1. 2019Online Learning: A Modern Introduction Using Convex Optimizationcited by 417
  2. 2019Online Control with Adversarial Disturbancescited by 92
  3. 2020Improper Learning for Non-Stochastic Controlcited by 83
  4. 2013Online Learning with Switching Costs and Other Adaptive Adversariescited by 61
  5. 2018Online Linear Quadratic Controlcited by 56
  6. 2019The Nonstochastic Control Problemcited by 52
  7. 2020Logarithmic Regret for Adversarial Online Controlcited by 41
  8. 2019Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysiscited by 40
  9. 2019Logarithmic Regret for Online Controlcited by 38
  10. 2020Adaptive Regret for Control of Time-Varying Dynamicscited by 38
  11. 2021Non-stationary Online Learning with Memory and Non-stochastic Controlcited by 33
  12. 2020The Power of Predictions in Online Controlcited by 31
17 more
  1. 2020Making Non-Stochastic Control (Almost) as Easy as Stochasticcited by 24
  2. 2020Online Optimal Control with Affine Constraintscited by 20
  3. 2022Introduction to Online Controlcited by 19
  4. 2020Non-Stochastic Control with Bandit Feedbackcited by 17
  5. 2015Online Convex Optimization Using Predictionscited by 16
  6. 2021Adversarial Tracking Control via Strongly Adaptive Online Learning with Memorycited by 14
  7. 2021Robustness and Consistency in Linear Quadratic Control with Untrusted Predictionscited by 14
  8. 2023No-Regret Online Reinforcement Learning with Adversarial Losses and Transitionscited by 13
  9. 2022Optimism in Face of a Context: Regret Guarantees for Stochastic Contextual MDPcited by 11
  10. 2022Optimistic No-regret Algorithms for Discrete Cachingcited by 10
  11. 2020Competitive Control with Delayed Imperfect Informationcited by 8
  12. 2021Machine Learning for Mechanical Ventilation Controlcited by 8
  13. 2021Competitive Controlcited by 8
  14. 2022Best of Both Worlds in Online Control: Competitive Ratio and Policy Regretcited by 6
  15. 2022On the Regret of H∞ Controlcited by 5
  16. 2023Online Nonstochastic Control with Adversarial and Static Constraintscited by 5
  17. 2022Online Caching with no Regret: Optimistic Learning via Recommendationscited by 4

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2024Optimistic Online Non-stochastic Control via FTRLcited by 3
  2. 2025Optimistic Learning for Communication Networkscited by 0
  3. 2025Smoothed Online Optimization for Target Tracking: Robust and Learning-Augmented Algorithmscited by 0