Meta-Adaptive Nonlinear Control: Theory and Algorithms

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 $\text{environment-dependent}$ 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.

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

References in corpus (6)

• Online Meta-Learning
• Learning-to-Learn Stochastic Gradient Descent with Biased Regularization
• Certainty Equivalence is Efficient for Linear Quadratic Control
• Information Theoretic Regret Bounds for Online Nonlinear Control
• Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems
• A Regret Minimization Approach to Iterative Learning Control