Meta-Adaptive Nonlinear Control: Theory and Algorithms

2021/06/11 by Guanya Shi, Shi, Guanya, Kamyar Azizzadenesheli +8 · 3 citations
Computer Science · Decision Sciences · Engineering · Physics and Astronomy · #Adaptive Dynamic Programming Control #Advanced Bandit Algorithms Research #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Robotics (cs.RO) #Systems and Control (eess.SY) #cs.AI #cs.LG #cs.RO #cs.SY #eess.SY #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2106.06098

35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia

openalex publication_date 2021/06/11 · arxiv created 2021/10/26 · arxiv updated 2021/10/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 environment-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.

Citations

• Adam: A Method for Stochastic Optimization
• Representation Learning: A Review and New Perspectives
• The Benefit of Multitask Representation Learning
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Spectral Normalization for Generative Adversarial Networks
• Meta-Reinforcement Learning of Structured Exploration Strategies
• Online Meta-Learning
• Certainty Equivalence is Efficient for Linear Quadratic Control
• Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning
• Provable Meta-Learning of Linear Representations
• Few-Shot Learning via Learning the Representation, Provably
• On the Theory of Transfer Learning: The Importance of Task Diversity
• A Regret Minimization Approach to Iterative Learning Control
• Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems
• Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions

Cited by

• Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning
• Leveraging Predictions in Power System Voltage Control: An Adaptive Approach
• Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Driving

Related

• Self-Supervised Meta-Learning for All-Layer DNN-Based Adaptive Control with Stability Guarantees
• Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems
• Hierarchical Meta-learning-based Adaptive Controller
• Control-oriented meta-learning
• Meta-Learning Online Control for Linear Dynamical Systems