Safe Online Convex Optimization with Unknown Linear Safety Constraints

11/14/2021
by   Sapana Chaudhary, et al.
0

We study the problem of safe online convex optimization, where the action at each time step must satisfy a set of linear safety constraints. The goal is to select a sequence of actions to minimize the regret without violating the safety constraints at any time step (with high probability). The parameters that specify the linear safety constraints are unknown to the algorithm. The algorithm has access to only the noisy observations of constraints for the chosen actions. We propose an algorithm, called the Safe Online Projected Gradient Descent (SO-PGD) algorithm, to address this problem. We show that, under the assumption of the availability of a safe baseline action, the SO-PGD algorithm achieves a regret O(T^2/3). While there are many algorithms for online convex optimization (OCO) problems with safety constraints available in the literature, they allow constraint violations during learning/optimization, and the focus has been on characterizing the cumulative constraint violations. To the best of our knowledge, ours is the first work that provides an algorithm with provable guarantees on the regret, without violating the linear safety constraints (with high probability) at any time step.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/23/2023

Dynamic Regret Analysis of Safe Distributed Online Optimization for Convex and Non-convex Problems

This paper addresses safe distributed online optimization over an unknow...
research
08/16/2019

Linear Stochastic Bandits Under Safety Constraints

Bandit algorithms have various application in safety-critical systems, w...
research
10/31/2021

Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees

We study the adaptive control of an unknown linear system with a quadrat...
research
12/19/2019

Log Barriers for Safe Non-convex Black-box Optimization

We address the problem of minimizing a smooth function f^0(x) over a com...
research
07/04/2023

Stranding Risk for Underactuated Vessels in Complex Ocean Currents: Analysis and Controllers

Low-propulsion vessels can take advantage of powerful ocean currents to ...
research
08/12/2017

Online Convex Optimization with Stochastic Constraints

This paper considers online convex optimization (OCO) with stochastic co...
research
01/24/2023

On Dynamic Regret and Constraint Violations in Constrained Online Convex Optimization

A constrained version of the online convex optimization (OCO) problem is...

Please sign up or login with your details

Forgot password? Click here to reset