Learning to OptimizeDownload PDF

Published: 06 Feb 2017, Last Modified: 22 Oct 2023ICLR 2017 PosterReaders: Everyone
Abstract: Algorithm design is a laborious process and often requires many iterations of ideation and validation. In this paper, we explore automating algorithm design and present a method to learn an optimization algorithm. We approach this problem from a reinforcement learning perspective and represent any particular optimization algorithm as a policy. We learn an optimization algorithm using guided policy search and demonstrate that the resulting algorithm outperforms existing hand-engineered algorithms in terms of convergence speed and/or the final objective value.
TL;DR: We explore learning an optimization algorithm automatically.
Conflicts: eecs.berkeley.edu
Keywords: Reinforcement Learning, Optimization
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:1606.01885/code)
20 Replies

Loading