Dynamic Algorithm Configuration

Funding Agency

We will model the algorithm control as a reinforcement learning (RL) problem, which means that the actions change parameter configurations, and the states correspond to the states of an algorithm solving a problem instance. Deep RL recently showed that challenging problems can be learned, e.g., the game of Go, playing Atari games or Poker. We believe that the recent progress in deep RL will enable us to successfully obtain effective control policies and we dub our approach deep algorithm control (DAC). DAC is similar to these game applications and therefore a promising research direction: (i) we can collect large amounts of training data in an offline phase by evaluating different policies on sets of instances, (ii) the state and action space is in both applications huge, and (iii) deep learning models can predict the performance of AI algorithms.

By successfully obtaining effective DAC policies, this approach will be a powerful generalization of other meta-algorithmic approaches, such as algorithm configuration, algorithm selection and their combinations. Thus we believe that DAC is a promising research direction that will have a huge impact on many AI fields such as algorithm configuration and algorithm selection previously had.

Lead at LUHAI: Prof. Lindauer

Funding Program:  DFG

Project Period: 2020-2024

Publications

Showing results 1 - 9 out of 9

2022


Adriaensen, S., Biedenkapp, A., Shala, G., Awad, N., Eimer, T., Lindauer, M., & Hutter, F. (2022). Automated Dynamic Algorithm Configuration. Journal of Artificial Intelligence Research, 75, 1633-1699. https://doi.org/10.48550/arXiv.2205.13881, https://doi.org/10.1613/jair.1.13922
Benjamins, C., Raponi, E., Jankovic, A., Blom, K. V. D., Santoni, M. L., Lindauer, M., & Doerr, C. (2022). PI is back! Switching Acquisition Functions in Bayesian Optimization. Advance online publication. https://arxiv.org/abs/2211.01455
Benjamins, C., Jankovic, A., Raponi, E., Blom, K. V. D., Lindauer, M., & Doerr, C. (2022). Towards Automated Design of Bayesian Optimization via Exploratory Landscape Analysis. Paper presented at Workshop on Meta-Learning (MetaLearn 2022). https://openreview.net/forum?id=cmxtTF_IHd

2021


Biedenkapp, A., Rajan, R., Hutter, F., & Lindauer, M. (2021). TempoRL: Learning When to Act. In Proceedings of the international conference on machine learning (ICML) Advance online publication. https://arxiv.org/abs/2106.05262
Eimer, T., Biedenkapp, A., Reimer, M., Adriaensen, S., Hutter, F., & Lindauer, M. T. (2021). DACBench: A Benchmark Library for Dynamic Algorithm Configuration. In Z.-H. Zhou (Ed.), Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21) (pp. 1668-1674). (IJCAI International Joint Conference on Artificial Intelligence). https://doi.org/10.24963/ijcai.2021/230
Eimer, T., Benjamins, C., & Lindauer, M. T. (2021). Hyperparameters in Contextual RL are Highly Situational. In International Workshop on Ecological Theory of RL (at NeurIPS) https://doi.org/10.48550/arXiv.2212.10876
Eimer, T., Biedenkapp, A., Hutter, F., & Lindauer, M. (2021). Self-Paced Context Evaluation for Contextual Reinforcement Learning. In Proceedings of the international conference on machine learning (ICML) Advance online publication. https://www.tnt.uni-hannover.de/papers/data/1454/space.pdf
Speck, D., Biedenkapp, A., Hutter, F., Mattmüller, R., & Lindauer, M. (2021). Learning Heuristic Selection with Dynamic Algorithm Configuration. In S. Biundo, M. Do, R. Goldman, M. Katz, Q. Yang, & H. H. Zhuo (Eds.), Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS) (pp. 597-605). (Proceedings International Conference on Automated Planning and Scheduling, ICAPS; Vol. 2021-August). https://doi.org/10.1609/icaps.v31i1.16008

2020


Biedenkapp, A., Bozkurt, H. F., Eimer, T., Hutter, F., & Lindauer, M. T. (2020). Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic Framework. In G. De Giacomo, A. Catala, B. Dilkina, M. Milano, S. Barro, A. Bugarin, & J. Lang (Eds.), ECAI 2020 - 24th European Conference on Artificial Intelligence (pp. 427-434). (Frontiers in Artificial Intelligence and Applications; Vol. 325). https://doi.org/10.3233/FAIA200122