# Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration

arXiv: https://arxiv.org/abs/2202.03259 · HTML: https://mlsanity.com/paper/2202.03259/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 67 references that are in the map.
- First posted on arXiv 7 Feb 2022.

## Builds on (most cited first, 20 of 20)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [Contextual Markov Decision Processes](https://mlsanity.com/paper/1502.02259/) (2015)
- [ParamILS: An Automatic Algorithm Configuration Framework](https://mlsanity.com/paper/1401.3492/) (2014)
- [Automated Reinforcement Learning (AutoRL): A Survey and Open Problems](https://mlsanity.com/paper/2201.03916/) (2022)
- [Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits](https://mlsanity.com/paper/2002.02518/) (2020)
- [Deep Reinforcement Learning Based Parameter Control in Differential Evolution](https://mlsanity.com/paper/1905.08006/) (2019)
- [DACBench: A Benchmark Library for Dynamic Algorithm Configuration](https://mlsanity.com/paper/2105.08541/) (2021)
- [Learning Heuristic Selection with Dynamic Algorithm Configuration](https://mlsanity.com/paper/2006.08246/) (2020)
- [Better Runtime Guarantees Via Stochastic Domination](https://mlsanity.com/paper/1801.04487/) (2018)
- [Self-Adjusting Mutation Rates with Provably Optimal Success Rules](https://mlsanity.com/paper/1902.02588/) (2019)
- [Online Selection of CMA-ES Variants](https://mlsanity.com/paper/1904.07801/) (2019)
- [Optimal Parameter Choices via Precise Black-Box Analysis](https://mlsanity.com/paper/1807.03403/) (2018)
- [The Query Complexity of a Permutation-Based Variant of Mastermind](https://mlsanity.com/paper/1812.08480/) (2018)
- [Optimal Mutation Rates for the (1+λ) EA on OneMax](https://mlsanity.com/paper/2006.11457/) (2020)
- [Maximizing Drift is Not Optimal for Solving OneMax](https://mlsanity.com/paper/1904.07818/) (2019)
- [The (1+1) Elitist Black-Box Complexity of LeadingOnes](https://mlsanity.com/paper/1604.02355/) (2016)
- [Optimal Static Mutation Strength Distributions for the (1+λ) Evolutionary Algorithm on OneMax](https://mlsanity.com/paper/2102.04944/) (2021)

## Built on by (most cited first, 11 of 11)

- [Automated Dynamic Algorithm Configuration](https://mlsanity.com/paper/2205.13881/) (2022)
- [Multi-agent Dynamic Algorithm Configuration](https://mlsanity.com/paper/2210.06835/) (2022)
- [Using Automated Algorithm Configuration for Parameter Control](https://mlsanity.com/paper/2302.12334/) (2023)
- [On the Importance of Reward Design in Reinforcement Learning-based Dynamic Algorithm Configuration: A Case Study on OneMax with (1+(λ,λ))-GA](https://mlsanity.com/paper/2502.20265/) (2025)
- [CANDID DAC: Leveraging Coupled Action Dimensions with Importance Differences in DAC](https://mlsanity.com/paper/2407.05789/) (2024)
- [Towards Automated Design of Bayesian Optimization via Exploratory Landscape Analysis](https://mlsanity.com/paper/2211.09678/) (2022)
- [Multi-parameter Control for the (1+(λ,λ))-GA on OneMax via Deep Reinforcement Learning](https://mlsanity.com/paper/2505.12982/) (2025)
- [Deep Reinforcement Learning for Dynamic Algorithm Configuration: A Case Study on Optimizing OneMax with the (1+(λ,λ))-GA](https://mlsanity.com/paper/2512.03805/) (2025)
- [Selection Hyper-heuristics Can Automatically Adjust the Learning Period to Optimally Solve Pseudo-Boolean Problems](https://mlsanity.com/paper/2605.29916/) (2026)
- [AI Training Manager: Bounded Closed-Loop Control of Adaptive Training Recipes](https://mlsanity.com/paper/2606.29871/) (2026)
- [Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learning](https://mlsanity.com/paper/2606.10129/) (2026)

## Abstract (arXiv)

It has long been observed that the performance of evolutionary algorithms and other randomized search heuristics can benefit from a non-static choice of the parameters that steer their optimization behavior. Mechanisms that identify suitable configurations on the fly ("parameter control") or via a dedicated training process ("dynamic algorithm configuration") are therefore an important component of modern evolutionary computation frameworks. Several approaches to address the dynamic parameter setting problem exist, but we barely understand which ones to prefer for which applications. As in classical benchmarking, problem collections with a known ground truth can offer very meaningful insights in this context. Unfortunately, settings with well-understood control policies are very rare. One of the few exceptions for which we know which parameter settings minimize the expected runtime is the LeadingOnes problem. We extend this benchmark by analyzing optimal control policies that can select the parameters only from a given portfolio of possible values. This also allows us to compute optimal parameter portfolios of a given size. We demonstrate the usefulness of our benchmarks by analyzing the behavior of the DDQN reinforcement learning approach for dynamic algorithm configuration.