Bayesian Optimization for Policy Search in High-Dimensional Systems via Automatic Domain Selection

Open access
Date
2019Type
- Conference Paper
Abstract
Bayesian Optimization (BO) is an effective method for optimizing expensive-to-evaluate black-box functions with a wide range of applications for example in robotics, system design and parameter optimization. However, scaling BO to problems with large input dimensions (>10) remains an open challenge. In this paper, we propose to leverage results from optimal control to scale BO to higher dimensional control tasks and to reduce the need for manually selecting the optimization domain. The contributions of this paper are twofold: 1) We show how we can make use of a learned dynamics model in combination with a model-based controller to simplify the BO problem by focusing onto the most relevant regions of the optimization domain. 2) Based on (1) we present a method to find an embedding in parameter space that reduces the effective dimensionality of the optimization problem. To evaluate the effectiveness of the proposed approach, we present an experimental evaluation on real hardware, as well as simulated tasks including a 48-dimensional policy for a quadcopter. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000394038Publication status
publishedExternal links
Book title
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)Pages / Article No.
Publisher
IEEEEvent
Subject
Bayesian optimization; Policy Search; Optimal Control and OptimizationOrganisational unit
09563 - Zeilinger, Melanie / Zeilinger, Melanie
Funding
157601 - Safety and Performance for Human in the Loop Control (SNF)
Notes
Conference lecture held on November 5, 2019More
Show all metadata