mlsanityData to 7 Oct 2026

Active Learning for Nonlinear System Identification with Guarantees

arXiv 2006.10277 ↗First posted 18 Jun 2020stat.ML cs.LG math.OCcited by 78

Not on the map. Why?

Abstract (arXiv)

While the identification of nonlinear dynamical systems is a fundamental building block of model-based reinforcement learning and feedback control, its sample complexity is only understood for systems that either have discrete states and actions or for systems that can be identified from data generated by i.i.d. random inputs. Nonetheless, many interesting dynamical systems have continuous states and actions and can only be identified through a judicious choice of inputs. Motivated by practical settings, we study a class of nonlinear dynamical systems whose state transitions depend linearly on a known feature embedding of state-action pairs. To estimate such systems in finite time identification methods must explore all directions in feature space. We propose an active learning approach that achieves this by repeating three steps: trajectory planning, trajectory tracking, and re-estimation of the system from all available data. We show that our method estimates nonlinear dynamical systems at a parametric rate, similar to the statistical rate of standard linear regression.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 16; 2023: 15; 2024: 18; 2025: 13; 2026: 3.

78 papers.

Sort:

By area:

  1. 2023Transformers as Algorithms: Generalization and Stability in In-context Learningcited by 220
  2. 2021Representation Learning for Online and Offline RL in Low-rank MDPscited by 128
  3. 2022Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learningcited by 125
  4. 2022Statistical Learning Theory for Control: A Finite Sample Perspectivecited by 52
  5. 2021Instrumental Variable Value Iteration for Causal Offline Reinforcement Learningcited by 35
  6. 2024From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformerscited by 34
  7. 2023Optimistic Active Exploration of Dynamical Systemscited by 32
  8. 2022Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexitycited by 31
  9. 2022A General Framework for Sample-Efficient Function Approximation in Reinforcement Learningcited by 31
  10. 2024MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximizationcited by 30
  11. 2024ASID: Active Exploration for System Identification in Robotic Manipulationcited by 27
  12. 2022Single Trajectory Nonparametric Learning of Nonlinear Dynamicscited by 26
38 more
  1. 2021A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learningcited by 24
  2. 2021Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systemscited by 17
  3. 2023Optimal Exploration for Model-Based RL in Nonlinear Systemscited by 17
  4. 2021Task-Optimal Exploration in Linear Dynamical Systemscited by 15
  5. 2022Learning Mixtures of Linear Dynamical Systemscited by 15
  6. 2021PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Explorationcited by 14
  7. 2022Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Samplingcited by 10
  8. 2021Sparsity in Partially Controllable Linear Systemscited by 9
  9. 2023Smoothed Online Learning for Prediction in Piecewise Affine Systemscited by 9
  10. 2021Adaptive Robust Model Predictive Control with Matched and Unmatched Uncertaintycited by 7
  11. 2022GD-VAEs: Geometric Dynamic Variational Autoencoders for Learning Nonlinear Dynamics and Dimension Reductionscited by 7
  12. 2024Active Learning for Control-Oriented Identification of Nonlinear Systemscited by 7
  13. 2025SOMBRL: Scalable and Optimistic Model-Based RLcited by 7
  14. 2024Beyond Optimism: Exploration With Partially Observable Rewardscited by 6
  15. 2024Learning Linear Dynamics from Bilinear Observationscited by 6
  16. 2021Koopman Spectrum Nonlinear Regulators and Efficient Online Learningcited by 5
  17. 2021Exponential Family Model-Based Reinforcement Learning via Score Matchingcited by 5
  18. 2022KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systemscited by 5
  19. 2022Offline Estimation of Controlled Markov Chains: Minimaxity and Sample Complexitycited by 5
  20. 2023Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Makingcited by 5
  21. 2023Non-asymptotic System Identification for Linear Systems with Nonlinear Policiescited by 5
  22. 2024Model Predictive Control and Reinforcement Learning: A Unified Framework Based on Dynamic Programmingcited by 5
  23. 2026LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Searchcited by 5
  24. 2021Robust Online Control with Model Misspecificationcited by 4
  25. 2023PAC-Bayes Generalisation Bounds for Dynamical Systems Including Stable RNNscited by 4
  26. 2025Finite Sample Identification of Partially Observed Bilinear Dynamical Systemscited by 4
  27. 2025KKL Observer Synthesis for Nonlinear Systems via Physics-Informed Learningcited by 4
  28. 2022Autoregressive Banditscited by 3
  29. 2023The Power of Learned Locally Linear Models for Nonlinear Policy Optimizationcited by 3
  30. 2023Learning Linearized Models from Nonlinear Systems with Finite Datacited by 3
  31. 2024NeoRL: Efficient Exploration for Nonepisodic RLcited by 3
  32. 2024Random Features Approximation for Control-Affine Systemscited by 3
  33. 2024Active Symbolic Discovery of Ordinary Differential Equations via Phase Portrait Sketchingcited by 3
  34. 2024Long-Context Linear System Identificationcited by 3
  35. 2024First, Learn What You Don't Know: Active Information Gathering for Driving at the Limits of Handlingcited by 3
  36. 2025Information theory and discriminative sampling for model discoverycited by 3
  37. 2021Towards a Dimension-Free Understanding of Adaptive Linear Controlcited by 2
  38. 2023FLEX: an Adaptive Exploration Algorithm for Nonlinear Systemscited by 2

50 most cited of 78 All 78 (JSON)