mlsanityData to 7 Oct 2026

Meta-Adaptive Nonlinear Control: Theory and Algorithms

arXiv 2106.06098 ↗First posted 11 Jun 2021cs.LG cs.AI cs.ROcited by 23

Not on the map. Why?

Abstract (arXiv)

We present an online multi-task learning approach for adaptive nonlinear control, which we call Online Meta-Adaptive Control (OMAC). The goal is to control a nonlinear system subject to adversarial disturbance and unknown textitenvironment-dependent nonlinear dynamics, under the assumption that the environment-dependent dynamics can be well captured with some shared representation. Our approach is motivated by robot control, where a robotic system encounters a sequence of new environmental conditions that it must quickly adapt to. A key emphasis is to integrate online representation learning with established methods from control theory, in order to arrive at a unified framework that yields both control-theoretic and learning-theoretic guarantees. We provide instantiations of our approach under varying conditions, leading to the first non-asymptotic end-to-end convergence guarantee for multi-task nonlinear control. OMAC can also be integrated with deep representation learning. Experiments show that OMAC significantly outperforms conventional adaptive control approaches which do not learn the shared representation, in inverted pendulum and 6-DoF drone control tasks under varying wind conditions.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 11 Jun 2021.

Builds on

35 of 53 references.

References · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  4. 2019Introduction to Online Convex Optimizationcited by 793
  5. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  6. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
  7. 2018Meta-Learning: A Surveycited by 254
  8. 2020Few-Shot Learning via Learning the Representation, Provablycited by 213
  9. 2019DeepMDP: Learning Continuous Latent Space Models for Representation Learningcited by 204
  10. 2015The Benefit of Multitask Representation Learningcited by 194
  11. 2020On the Theory of Transfer Learning: The Importance of Task Diversitycited by 186
  12. 2019Adaptive Gradient-Based Meta-Learning Methodscited by 183
23 more
  1. 2020Provable Meta-Learning of Linear Representationscited by 161
  2. 2017On the Sample Complexity of the Linear Quadratic Regulatorcited by 151
  3. 2019TossingBot: Learning to Throw Arbitrary Objects with Residual Physicscited by 131
  4. 2018Meta-Reinforcement Learning of Structured Exploration Strategiescited by 128
  5. 2018State Representation Learning for Control: An Overviewcited by 125
  6. 2020Naive Exploration is Optimal for Online LQRcited by 111
  7. 2020Information Theoretic Regret Bounds for Online Nonlinear Controlcited by 87
  8. 2018Neural Lander: Stable Drone Landing Control using Learned Dynamicscited by 82
  9. 2018Online Linear Quadratic Controlcited by 55
  10. 2019Learning-to-Learn Stochastic Gradient Descent with Biased Regularizationcited by 49
  11. 2020Logarithmic Regret Bound in Partially Observable Linear Dynamical Systemscited by 46
  12. 2019Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysiscited by 40
  13. 2021Adaptive-Control-Oriented Meta-Learning for Nonlinear Systemscited by 38
  14. 2020The Power of Predictions in Online Controlcited by 31
  15. 2019Learning Causal State Representations of Partially Observable Environmentscited by 30
  16. 2020Regret Bounds for Adaptive Nonlinear Controlcited by 25
  17. 2019Robust Regression for Safe Exploration in Controlcited by 24
  18. 2020Neural-Swarm: Decentralized Close-Proximity Multirotor Control Using Learned Interactionscited by 19
  19. 2020Neural-Swarm2: Planning and Control of Heterogeneous Multirotor Swarms using Learned Interactionscited by 19
  20. 2015Regret Guarantees for Item-Item Collaborative Filteringcited by 11
  21. 2021A Regret Minimization Approach to Iterative Learning Controlcited by 8
  22. 2021Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditionscited by 8
  23. 2020Adaptive Nonlinear Control of Fixed-Wing VTOL with Airflow Vector Sensingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 11; 2024: 4; 2025: 2; 2026: 2.

23 papers.

Sort:

By area:

  1. 2022Neural-Fly Enables Rapid Learning for Agile Flight in Strong Windscited by 80
  2. 2022Multi-Task Imitation Learning for Linear Dynamical Systemscited by 22
  3. 2023Optimal Exploration for Model-Based RL in Nonlinear Systemscited by 17
  4. 2023Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Datacited by 12
  5. 2023Improved Active Multi-Task Representation Learning via Lassocited by 9
  6. 2023Safe Deep Policy Adaptationcited by 9
  7. 2023Constrained Meta-Reinforcement Learning for Adaptable Safety Guarantee with Differentiable Convex Programmingcited by 8
  8. 2021Adaptive Control of SE(3) Hamiltonian Dynamics with Learned Disturbance Featurescited by 6
  9. 2024Solving Continual Offline Reinforcement Learning with Decision Transformercited by 6
  10. 2021Online Optimization with Feedback Delay and Nonlinear Switching Costcited by 5
  11. 2024Decision Transformer as a Foundation Model for Partially Observable Continuous Controlcited by 5
  12. 2025Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Drivingcited by 3
11 more
  1. 2023Continual Visual Reinforcement Learning with A Life-Long World Modelcited by 2
  2. 2023Active Representation Learning for General Task Space with Applications in Roboticscited by 2
  3. 2023Meta-Learning-Based Adaptive Stability Certificates for Dynamical Systemscited by 2
  4. 2024Combining Federated Learning and Control: A Surveycited by 2
  5. 2025Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learningcited by 2
  6. 2023Distributionally Safe Reinforcement Learning under Model Uncertainty: A Single-Level Approach by Differentiable Convex Programmingcited by 1
  7. 2023Data-Guided Regulator for Adaptive Nonlinear Controlcited by 0
  8. 2023Domain Invariant Learning for Gaussian Processes and Bayesian Explorationcited by 0
  9. 2024Model-Free versus Model-Based Reinforcement Learning for Fixed-Wing UAV Attitude Control Under Varying Wind Conditionscited by 0
  10. 2026T2S-MPC: Time-Embedded Online Adaptive Model Predictive Control for Time-Varying Dynamicscited by 0
  11. 2026Neural ODEs Meet Concurrent Learning: Stable Online Learning with Lyapunov Guaranteescited by 0