DeepAI AI Chat
Log In Sign Up

Meta-Adaptive Nonlinear Control: Theory and Algorithms

by   Guanya Shi, et al.

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 adaptive 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.


page 1

page 2

page 3

page 4


Adaptive Robust Model Predictive Control via Uncertainty Cancellation

We propose a learning-based robust predictive control algorithm that com...

Distributed Multi-Task Learning with Shared Representation

We study the problem of distributed multi-task learning with shared repr...

Adaptive Robust Model Predictive Control with Matched and Unmatched Uncertainty

We propose a learning-based robust predictive control algorithm that can...

Task-Driven Estimation and Control via Information Bottlenecks

Our goal is to develop a principled and general algorithmic framework fo...

Representation Learning for Context-Dependent Decision-Making

Humans are capable of adjusting to changing environments flexibly and qu...

Neural Lyapunov Control

We propose new methods for learning control policies and neural network ...

Multi-Task Generative Adversarial Nets with Shared Memory for Cross-Domain Coordination Control

Generating sequential decision process from huge amounts of measured pro...

Code Repositories



view repo