Maintained by Steven Adriaensen and André Biedenkapp.
The following list considers papers related to dynamic algorithm configuration. It is by no means complete. If you miss a paper on the list, please let us know.
Please note that dynamic configuration has been studied in many different communities (under many different names) and each community has developed a slightly different focus or evaluation criteria. Our criteria for maintaining this literature list are as follows:
- Does the presented work change (hyper-)parameters on the fly (i.e., during the run of a target algorithm)?
- Is this done in an automated fashion (e.g., via a learned update policy)?
- Does it have a meta-learning component (i.e., can the configuration policies be transferred to problems that it has not been ‘learned’ on)?
2022
Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration Inproceedings Forthcoming
In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO'22), Forthcoming.
2021
Learning to Switch Optimizers for Quadratic Programming Inproceedings
In: Balasubramanian, Vineeth N.; Tsang, Ivor (Ed.): Proceedings of The 13th Asian Conference on Machine Learning, pp. 1553–1568, PMLR, 2021.
Sparsely Ensembled Convolutional Neural Network Classifiers via Reinforcement Learning Inproceedings
In: 2021 6th International Conference on Machine Learning Technologies, pp. 102–110, 2021, ISBN: 9781450389402.
MetaREVEAL: RL-based Meta-learning from Learning Curves Inproceedings
In: Workshop on Interactive Adaptive Learning co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2021), 2021.
Accelerating Quadratic Optimization with Reinforcement Learning Unpublished
2021.
Learning Heuristic Selection with Dynamic Algorithm Configuration Inproceedings
In: Zhuo, H H; Yang, Q; Do, M; Goldman, R; Biundo, S; Katz, M (Ed.): Proceedings of the 31st International Conference on Automated Planning and Scheduling (ICAPS'21), pp. 597–605, AAAI, 2021.
DACBench: A Benchmark Library for Dynamic Algorithm Configuration Inproceedings
In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI'21), ijcai.org, 2021.
A Generalizable Approach to Learning Optimizers Unpublished
2021.
Tuning the Hyperparameters of Anytime Planning: A Deep Reinforcement Learning Approach Inproceedings
In: ICAPS 2021 Workshop on Heuristics and Search for Domain-independent Planning, 2021.
2020
Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic Framework Conference
Proceedings of the Twenty-fourth European Conference on Artificial Intelligence (ECAI'20), 2020.
Learning Neural Search Policies for Classical Planning Inproceedings
In: Proceedings of the International Conference on Automated Planning and Scheduling, pp. 522–530, 2020.
Learning Step-Size Adaptation in CMA-ES Inproceedings
In: Proceedings of the Sixteenth International Conference on Parallel Problem Solving from Nature (PPSN'20), pp. 691–706, Springer, 2020.
Time-Dependent Automatic Parameter Configuration of a Local Search Algorithm Inproceedings
In: Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion, pp. 1898–1905, Association for Computing Machinery, Cancún, Mexico, 2020, ISBN: 9781450371278.
2019
Learning an Adaptive Learning Rate Schedule Unpublished
2019, (textitarXiv:1909.09712 [cs.LG]).
Deep reinforcement learning based parameter control in differential evolution Inproceedings
In: Auger, A; ü, St T (Ed.): Proceedings of the Genetic and Evolutionary Computation Conference (GECCO'19), pp. 709–717, ACM, 2019.
Learning classical planning strategies with policy gradient Inproceedings
In: Proceedings of the International Conference on Automated Planning and Scheduling, pp. 637–645, 2019.
2017
Reactive Dialectic Search Portfolios for MaxSAT Inproceedings
In: S.Singh,; Markovitch, S (Ed.): Proceedings of the Conference on Artificial Intelligence (AAAI'17), pp. 765–772, AAAI Press, 2017.
Reinforcement learning for learning rate control Journal Article
In: arXiv preprint arXiv:1705.11159, 2017.
Learning a reactive restart strategy to improve stochastic search Inproceedings
In: International Conference on Learning and Intelligent Optimization, pp. 109–123, Springer 2017.
2016
Towards a White Box Approach to Automated Algorithm Design Inproceedings
In: Kambhampati, S (Ed.): Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI'16), pp. 554–560, 2016.
Using Deep Q-Learning to Control Optimization Hyperparameters Journal Article
In: arXiv preprint arXiv:1602.04062, 2016.
Tuning of Multiple Parameter Sets in Evolutionary Algorithms Inproceedings
In: Proceedings of the Genetic and Evolutionary Computation Conference 2016, pp. 533–540, 2016.
Learning Step Size Controllers for Robust Neural Network Training Inproceedings
In: Schuurmans, D; Wellman, M (Ed.): Proceedings of the Thirtieth National Conference on Artificial Intelligence (AAAI'16), AAAI Press, 2016.
2014
Automatically Improving the Anytime Behaviour of Optimisation Algorithms Journal Article
In: European Journal of Operational Research, vol. 235, no. 3, pp. 569–582, 2014.
2012
An Investigation of Reinforcement Learning for Reactive Search Optimization Incollection
In: Hamadi, Y; Monfroy, E; Saubion, F (Ed.): Autonomous Search, pp. 131–160, Springer, 2012.
2010
Iterative Learning of Weighted Rule Sets for Greedy Search Conference
Proceedings of the 20th International Conference on Automated Planning and Scheduling (ICAPS'10), 2010.
A Method to Control Parameters of Evolutionary Algorithms by Using Reinforcement Learning Inproceedings
In: é, K Y; Dipanda, A; Chbeir, R (Ed.): Proceedings of Sixth International Conference on Signal-Image Technology and Internet-Based Systems (SITIS), pp. 74–79, IEEE Computer Society, 2010.
Analyzing Bandit-Based Adaptive Operator Selection Mechanisms Journal Article
In: Annals of Mathematics and Artificial Intelligence, vol. 60, no. 1, pp. 25–64, 2010.
2002
Controlling Genetic Algorithms with Reinforcement Learning Inproceedings
In: Proceedings of the 4th Annual Conference on Genetic and Evolutionary Computation, pp. 692–692, 2002.
2001
Learning to Select Branching Rules in the DPLL Procedure for Satisfiability Journal Article
In: Electronic Notes in Discrete Mathematics, vol. 9, pp. 344–359, 2001.
2000
Algorithm Selection using Reinforcement Learning Conference
Proceedings of the 17th International Conference on Machine Learning (ICML 2000), 2000.