Robust Regression for Safe Exploration in Control

06/13/2019
by   Anqi Liu, et al.
1

We study the problem of safe learning and exploration in sequential control problems. The goal is to safely collect data samples from an operating environment to learn an optimal controller. A central challenge in this setting is how to quantify uncertainty in order to choose provably-safe actions that allow us to collect useful data and reduce uncertainty, thereby achieving both improved safety and optimality. To address this challenge, we present a deep robust regression model that is trained to directly predict the uncertainty bounds for safe exploration. We then show how to integrate our robust regression approach with model-based control methods by learning a dynamic model with robustness bounds. We derive generalization bounds under domain shifts for learning and connect them with safety and stability bounds in control. We demonstrate empirically that our robust regression approach can outperform conventional Gaussian process (GP) based safe exploration in settings where it is difficult to specify a good GP prior.

READ FULL TEXT
research
09/08/2020

ℛℒ_1-𝒢𝒫: Safe Simultaneous Learning and Control

We present ℛℒ_1-𝒢𝒫, a control framework that enables safe simultaneous l...
research
11/09/2018

Reachability-based safe learning for optimal control problem

In this work we seek for an approach to integrate safety in the learning...
research
11/15/2019

Safe Interactive Model-Based Learning

Control applications present hard operational constraints. A violation o...
research
05/05/2020

Regret Bounds for Safe Gaussian Process Bandit Optimization

Many applications require a learner to make sequential decisions given u...
research
10/04/2022

Safe and Stable Control Synthesis for Uncertain System Models via Distributionally Robust Optimization

This paper considers enforcing safety and stability of dynamical systems...
research
12/09/2022

Information-Theoretic Safe Exploration with Gaussian Processes

We consider a sequential decision making task where we are not allowed t...
research
05/06/2021

Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression

Gaussian Process Regression is a popular nonparametric regression method...

Please sign up or login with your details

Forgot password? Click here to reset