Meta-Adaptive Nonlinear Control: Theory and Algorithms
arXiv:2106.06098
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 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.
arXiv comment35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia
References in corpus (19)
- Adam: A Method for Stochastic Optimization
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Spectral Normalization for Generative Adversarial Networks
- State Representation Learning for Control: An Overview
- Neural Lander: Stable Drone Landing Control using Learned Dynamics
- Meta-Reinforcement Learning of Structured Exploration Strategies
- The Benefit of Multitask Representation Learning
- Online Meta-Learning
- On the Theory of Transfer Learning: The Importance of Task Diversity
- Few-Shot Learning via Learning the Representation, Provably
- Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis
- Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems
- Provable Meta-Learning of Linear Representations
- 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
- Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions
- A Regret Minimization Approach to Iterative Learning Control