mlsanityData to 7 Oct 2026

Online Control with Adversarial Disturbances

arXiv 1902.08721 ↗First posted 23 Feb 2019cs.LG cs.SY eess.SYcited by 92

Not on the map. Why?

Abstract (arXiv)

We study the control of a linear dynamical system with adversarial disturbances (as opposed to statistical noise). The objective we consider is one of regret: we desire an online control procedure that can do nearly as well as that of a procedure that has full knowledge of the disturbances in hindsight. Our main result is an efficient algorithm that provides nearly tight regret bounds for this problem. From a technical standpoint, this work generalizes upon previous work in two main aspects: our model allows for adversarial noise in the dynamics, and allows for general convex costs.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 23; 2023: 18; 2024: 13; 2025: 8; 2026: 6.

92 papers.

Sort:

By area:

  1. 2021Recurrent Equilibrium Networks: Flexible Dynamic Models with Guaranteed Stability and Robustnesscited by 43
  2. 2022Provable Reinforcement Learning with a Short-Term Memorycited by 40
  3. 2024Online DPO: Online Direct Preference Optimization with Fast-Slow Chasingcited by 38
  4. 2021Non-stationary Online Learning with Memory and Non-stochastic Controlcited by 33
  5. 2022Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexitycited by 31
  6. 2022Parameter-free Regret in High Probability with Heavy Tailscited by 26
  7. 2021Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Gamescited by 18
  8. 2021Streaming Linear System Identification with Reverse Experience Replaycited by 17
  9. 2021Task-Optimal Exploration in Linear Dynamical Systemscited by 15
  10. 2021Learning-to-learn non-convex piecewise-Lipschitz functionscited by 15
  11. 2023Efficient Methods for Non-stationary Online Learningcited by 15
  12. 2021Adversarial Tracking Control via Strongly Adaptive Online Learning with Memorycited by 14
38 more
  1. 2021Lazy OCO: Online Convex Optimization on a Switching Budgetcited by 14
  2. 2023Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregressioncited by 14
  3. 2022Online Control of Unknown Time-Varying Dynamical Systemscited by 13
  4. 2022Dynamic Regret of Online Markov Decision Processescited by 13
  5. 2025Online Convex Optimization with Heavy Tails: Old Algorithms, New Regrets, and Applicationscited by 13
  6. 2023Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Datacited by 12
  7. 2021Prospective Artificial Intelligence Approaches for Active Cyber Defencecited by 11
  8. 2021Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarkingcited by 10
  9. 2021Regret-optimal Estimation and Controlcited by 10
  10. 2021Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guaranteescited by 10
  11. 2022Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Samplingcited by 10
  12. 2021Learning from Censored and Dependent Data: The case of Linear Dynamicscited by 9
  13. 2022Optimal Comparator Adaptive Online Learning with Switching Costcited by 9
  14. 2023Smoothed Online Learning for Prediction in Piecewise Affine Systemscited by 9
  15. 2021A Regret Minimization Approach to Iterative Learning Controlcited by 8
  16. 2021Competitive Controlcited by 8
  17. 2022Adversarially Robust PAC Learnability of Real-Valued Functionscited by 8
  18. 2023Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictionscited by 8
  19. 2023Optimal Rates for Bandit Nonstochastic Controlcited by 7
  20. 2021Regret Analysis of Distributed Online LQR Control for Unknown LTI Systemscited by 6
  21. 2021Provable Regret Bounds for Deep Online Learning and Controlcited by 6
  22. 2022Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithmcited by 6
  23. 2022Adaptive Composite Online Optimization: Predictions in Static and Dynamic Environmentscited by 6
  24. 2022Optimal Dynamic Regret in LQR Controlcited by 6
  25. 2022Towards a Theoretical Foundation of Policy Optimization for Learning Control Policiescited by 6
  26. 2022Online Convex Optimization with Unbounded Memorycited by 6
  27. 2025Universal Sequence Preconditioningcited by 6
  28. 2021Online Optimization with Feedback Delay and Nonlinear Switching Costcited by 5
  29. 2022Rate-Optimal Online Convex Optimization in Adaptive Linear Controlcited by 5
  30. 2022Meta-Learning Online Control for Linear Dynamical Systemscited by 5
  31. 2022Best of Both Worlds in Online Control: Competitive Ratio and Policy Regretcited by 5
  32. 2023Efficient Online Learning with Memory via Frank-Wolfe Optimization: Algorithms with Bounded Dynamic Regret and Applications to Controlcited by 5
  33. 2023Online Nonstochastic Control with Adversarial and Static Constraintscited by 5
  34. 2023Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Makingcited by 5
  35. 2024Predictive Linear Online Tracking for Unknown Targetscited by 5
  36. 2025The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspectivecited by 5
  37. 2021Robust Online Control with Model Misspecificationcited by 4
  38. 2021Finite-time System Identification and Adaptive Control in Autoregressive Exogenous Systemscited by 4

50 most cited of 92 All 92 (JSON)