Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Non-asymptotic System Identification for Linear Systems with Nonlinear Policies (2306.10369v1)

Published 17 Jun 2023 in math.OC, cs.SY, eess.SY, and stat.ML

Abstract: This paper considers a single-trajectory system identification problem for linear systems under general nonlinear and/or time-varying policies with i.i.d. random excitation noises. The problem is motivated by safe learning-based control for constrained linear systems, where the safe policies during the learning process are usually nonlinear and time-varying for satisfying the state and input constraints. In this paper, we provide a non-asymptotic error bound for least square estimation when the data trajectory is generated by any nonlinear and/or time-varying policies as long as the generated state and action trajectories are bounded. This significantly generalizes the existing non-asymptotic guarantees for linear system identification, which usually consider i.i.d. random inputs or linear policies. Interestingly, our error bound is consistent with that for linear policies with respect to the dependence on the trajectory length, system dimensions, and excitation levels. Lastly, we demonstrate the applications of our results by safe learning with robust model predictive control and provide numerical analysis.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. Convergence properties of the membership set. Automatica, 34(10), 1245–1249.
  2. Necessary and sufficient conditions for parameter convergence in adaptive control. Automatica, 22(6), 629–639.
  3. Regret bounds for robust adaptive control of the linear quadratic regulator. In Advances in Neural Information Processing Systems, 4188–4197.
  4. On the sample complexity of the linear quadratic regulator. Foundations of Computational Mathematics, 1–47.
  5. Safely learning to control the constrained linear quadratic regulator. In 2019 American Control Conference (ACC), 5582–5588. IEEE.
  6. Regret analysis of learning-based mpc with partially-unknown cost function. arXiv preprint arXiv:2108.02307.
  7. A general safety framework for learning-based control in uncertain robotic systems. IEEE Transactions on Automatic Control, 64(7), 2737–2752.
  8. On the value of information in system identification—bounded noise case. Automatica, 18(2), 229–238.
  9. Learning nonlinear dynamical systems from a single trajectory. In Learning for Dynamics and Control, 851–861. PMLR.
  10. Linear robust adaptive model predictive control: Computational complexity and conservatism. In 2019 IEEE 58th Conference on Decision and Control (CDC), 1383–1388. IEEE.
  11. Online optimal control with affine constraints. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 8527–8537.
  12. Safe adaptive learning-based control for constrained linear quadratic regulators with regret guarantees. arXiv preprint arXiv:2111.00411.
  13. Robust tube-based mpc for tracking of constrained linear systems with additive disturbances. Journal of Process Control, 20(3), 248–260.
  14. Robust adaptive control barrier functions: An adaptive and data-driven approach to safety. IEEE Control Systems Letters, 5(3), 1031–1036.
  15. Robust mpc with recursive model update. Automatica, 103, 461–471.
  16. Active learning for nonlinear system identification with guarantees. Journal of Machine Learning Research, 23(32), 1–30.
  17. Learning the linear quadratic regulator from nonlinear observations. Advances in Neural Information Processing Systems, 33, 14532–14543.
  18. A tractable approximation of chance constrained stochastic mpc based on affine disturbance feedback. In 2008 47th IEEE conference on decision and control, 4731–4736. IEEE.
  19. Oymak, S. (2019). Stochastic gradient descent learns state equations with nonlinear activations. In A. Beygelzimer and D. Hsu (eds.), Proceedings of the Thirty-Second Conference on Learning Theory, volume 99 of Proceedings of Machine Learning Research, 2551–2579. PMLR.
  20. Non-asymptotic identification of lti systems from a single trajectory. In 2019 American control conference (ACC), 5655–5661. IEEE.
  21. Model predictive control: Theory and design. Nob Hill Pub.
  22. Learning discrete-time uncertain nonlinear systems with probabilistic safety and stability constraints. IEEE Open Journal of Control Systems.
  23. Near optimal finite time identification of arbitrary linear dynamical systems. In International Conference on Machine Learning, 5610–5618. PMLR.
  24. Non-asymptotic and accurate learning of nonlinear dynamical systems. Journal of Machine Learning Research, 23(140), 1–49.
  25. Finite sample identification of bilinear dynamical systems. arXiv preprint arXiv:2208.13915.
  26. Learning without mixing: Towards a sharp analysis of linear system identification. In Conference On Learning Theory, 439–473. PMLR.
  27. A control barrier perspective on episodic learning via projection-to-state safety. IEEE Control Systems Letters, 5(3), 1019–1024.
  28. Linear model predictive safety certification for learning-based control. In 2018 IEEE Conference on Decision and Control (CDC), 7130–7135. IEEE.
  29. Performance and safety of bayesian model predictive control: Scalable model-based rl with guarantees. arXiv preprint arXiv:2006.03483.
  30. Xu, X. (2018). Constrained control of input–output linearizable systems using control sharing barrier functions. Automatica, 87, 195–201.
  31. Adaptive sampling methods for learning dynamical systems. In Mathematical and Scientific Machine Learning, 335–350. PMLR.
  32. Learning with little mixing. arXiv preprint arXiv:2206.08269.
Citations (7)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now