BayesOpt: A Library for Bayesian optimization with Robotics Applications

TL;DR

This paper introduces BayesOpt, a versatile and fast software library for Bayesian optimization in robotics, enabling easy testing of various models and criteria, and demonstrating its efficiency on diverse problems.

Contribution

It presents a comprehensive, flexible toolbox for Bayesian optimization that includes state-of-the-art models and algorithms, facilitating broader application and testing.

Findings

The toolbox is fast and easy to use across multiple operating systems.

It includes most recent algorithms and models for Bayesian optimization.

The software demonstrates efficiency even on less expensive functions.

Abstract

The purpose of this paper is twofold. On one side, we present a general framework for Bayesian optimization and we compare it with some related fields in active learning and Bayesian numerical analysis. On the other hand, Bayesian optimization and related problems (bandits, sequential experimental design) are highly dependent on the surrogate model that is selected. However, there is no clear standard in the literature. Thus, we present a fast and flexible toolbox that allows to test and combine different models and criteria with little effort. It includes most of the state-of-the-art contributions, algorithms and models. Its speed also removes part of the stigma that Bayesian optimization methods are only good for "expensive functions". The software is free and it can be used in many operating systems and computer languages.