TY - GEN

T1 - DACBench: A Benchmark Library for Dynamic Algorithm Configuration

AU - Eimer, Theresa

AU - Biedenkapp, André

AU - Reimer, Maximilian

AU - Adriaensen, Steven

AU - Hutter, Frank

AU - Lindauer, Marius Thomas

N1 - Funding Information: We thank Gresa Shala, David Speck and Rishan Senanayake for their contributions to the CMA-ES, FastDownward and SGD-DL benchmarks respectively. Theresa Eimer and Marius Lindauer acknowledge funding by the German Research Foundation (DFG) under LI 2801/4-1. All authors acknowledge funding by the Robert Bosch GmbH.

PY - 2021

Y1 - 2021

N2 - Dynamic Algorithm Configuration (DAC) aims to dynamically control a target algorithm's hyperparameters in order to improve its performance. Several theoretical and empirical results have demonstrated the benefits of dynamically controlling hyperparameters in domains like evolutionary computation, AI Planning or deep learning. Replicating these results, as well as studying new methods for DAC, however, is difficult since existing benchmarks are often specialized and incompatible with the same interfaces. To facilitate benchmarking and thus research on DAC, we propose DACBench, a benchmark library that seeks to collect and standardize existing DAC benchmarks from different AI domains, as well as provide a template for new ones. For the design of DACBench, we focused on important desiderata, such as (i) flexibility, (ii) reproducibility, (iii) extensibility and (iv) automatic documentation and visualization. To show the potential, broad applicability and challenges of DAC, we explore how a set of six initial benchmarks compare in several dimensions of difficulty.

AB - Dynamic Algorithm Configuration (DAC) aims to dynamically control a target algorithm's hyperparameters in order to improve its performance. Several theoretical and empirical results have demonstrated the benefits of dynamically controlling hyperparameters in domains like evolutionary computation, AI Planning or deep learning. Replicating these results, as well as studying new methods for DAC, however, is difficult since existing benchmarks are often specialized and incompatible with the same interfaces. To facilitate benchmarking and thus research on DAC, we propose DACBench, a benchmark library that seeks to collect and standardize existing DAC benchmarks from different AI domains, as well as provide a template for new ones. For the design of DACBench, we focused on important desiderata, such as (i) flexibility, (ii) reproducibility, (iii) extensibility and (iv) automatic documentation and visualization. To show the potential, broad applicability and challenges of DAC, we explore how a set of six initial benchmarks compare in several dimensions of difficulty.

UR - http://www.scopus.com/inward/record.url?scp=85108817360&partnerID=8YFLogxK

U2 - 10.24963/ijcai.2021/230

DO - 10.24963/ijcai.2021/230

M3 - Conference contribution

T3 - IJCAI International Joint Conference on Artificial Intelligence

SP - 1668

EP - 1674

BT - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21)

A2 - Zhou, Zhi-Hua

ER -