DACBench: A Benchmark Library for Dynamic Algorithm Configuration

Eimer, Theresa; Biedenkapp, André; Reimer, Maximilian; Adriaensen, Steven; Hutter, Frank; Lindauer, Marius

doi:10.48550/arxiv.2105.08541

Cited by 5 publications

(3 citation statements)

References 20 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Looking at Context sets, we see that PCG is heavily used in ZSG environments, featuring in 21 (38%) environments. Many environments combine PCG components with controllable variation (Chevalier-Boisvert et al, 2019;Côté et al, 2019;Juliani et al, 2019;Li et al, 2021b;Team et al, 2021;Xue et al, 2021;Fortunato et al, 2019;Eimer et al, 2021;Bapst et al, 2019). Most environments have several different kinds of factors of variation within their context set.…”

Section: Trends In Environmentsmentioning

confidence: 99%

A Survey of Zero-shot Generalisation in Deep Reinforcement Learning

Kirk

Zhang²,

Grefenstette³

et al. 2023

jair

View full text Add to dashboard Cite

The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to produce RL algorithms whose policies generalise well to novel unseen situations at deployment time, avoiding overfitting to their training environments. Tackling this is vital if we are to deploy reinforcement learning algorithms in real world scenarios, where the environment will be diverse, dynamic and unpredictable. This survey is an overview of this nascent field. We rely on a unifying formalism and terminology for discussing different ZSG problems, building upon previous works. We go on to categorise existing benchmarks for ZSG, as well as current methods for tackling these problems. Finally, we provide a critical discussion of the current state of the field, including recommendations for future work. Among other conclusions, we argue that taking a purely procedural content generation approach to benchmark design is not conducive to progress in ZSG, we suggest fast online adaptation and tackling RL-specific problems as some areas for future work on methods for ZSG, and we recommend building benchmarks in underexplored problem settings such as offline RL ZSG and reward-function variation.

show abstract

Section: Trends In Environmentsmentioning

confidence: 99%

A Survey of Zero-shot Generalisation in Deep Reinforcement Learning

Kirk

Zhang²,

Grefenstette³

et al. 2023

jair

View full text Add to dashboard Cite

show abstract

“…when adapting strategy parameters of CMA-ES [30,33]. Because of this, most approaches for DAC are based on reinforcement learning [3]. However, the problem of DAC, and dynAS more specifically, can also be viewed as a hyperparameter optimization problem.…”

Section: Dynasmentioning

confidence: 99%

To Switch or Not to Switch: Predicting the Benefit of Switching Between Algorithms Based on Trajectory Features

Vermetten¹,

Wang²,

Sim³

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Dynamic algorithm selection aims to exploit the complementarity of multiple optimization algorithms by switching between them during the search. While these kinds of dynamic algorithms have been shown to have potential to outperform their component algorithms, it is still unclear how this potential can best be realized. One promising approach is to make use of landscape features to enable a per-run trajectory-based switch. Here, the samples seen by the first algorithm are used to create a set of features which describe the landscape from the perspective of the algorithm. These features are then used to predict what algorithm to switch to. In this work, we extend this per-run trajectory-based approach to consider a wide variety of potential points at which to perform the switch. We show that using a sliding window to capture the local landscape features contains information which can be used to predict whether a switch at that point would be beneficial to future performance. By analyzing the resulting models, we identify what features are most important to these predictions. Finally, by evaluating the importance of features and comparing these values between multiple algorithms, we show clear differences in the way the second algorithm interacts with the local landscape features found before the switch.

show abstract

“…of varying complexity (number of variables and problem instances) for tasks of runtime or quality configuration. For DAC, the DACBench has been proposed (Eimer et al, 2021), although this does not support DAC settings envisioned, e.g., by hyper-reactive search. As an alternative to such libraries, AC methods can also be benchmarked by using surrogate models that are trained on test instances in advance, resulting in cheaper evaluations when testing (Eggensperger et al, 2018).…”

Section: Novel Benchmarksmentioning

confidence: 99%

A Survey of Methods for Automated Algorithm Configuration

Schede

Brandt

Tornede

et al. 2022

jair

View full text Add to dashboard Cite

Algorithm configuration (AC) is concerned with the automated search of the most suitable parameter configuration of a parametrized algorithm. There is currently a wide variety of AC problem variants and methods proposed in the literature. Existing reviews do not take into account all derivatives of the AC problem, nor do they offer a complete classification scheme. To this end, we introduce taxonomies to describe the AC problem and features of configuration methods, respectively. We review existing AC literature within the lens of our taxonomies, outline relevant design choices of configuration approaches, contrast methods and problem variants against each other, and describe the state of AC in industry. Finally, our review provides researchers and practitioners with a look at future research directions in the field of AC.

show abstract

DACBench: A Benchmark Library for Dynamic Algorithm Configuration

Cited by 5 publications

References 20 publications

A Survey of Zero-shot Generalisation in Deep Reinforcement Learning

A Survey of Zero-shot Generalisation in Deep Reinforcement Learning

To Switch or Not to Switch: Predicting the Benefit of Switching Between Algorithms Based on Trajectory Features

A Survey of Methods for Automated Algorithm Configuration

Contact Info

Product

Resources

About