Automating Speedrun Routing: Overview and Vision
Abstract
Speedrunning in general means to play a video game fast, i.e. using all means at one's disposal to achieve a given goal in the least amount of time possible. To do so, a speedrun must be planned in advance, or routed, as referred to by the community. This paper focuses on discovering challenges and defining models needed when trying to approach the problem of routing algorithmically. To do so, this paper is split in two parts. The first part provides an overview of relevant speedrunning literature, extracting vital information and formulating criticism. Important categorizations are pointed out and a nomenclature is built to support professional discussion. The second part of this paper then refers to the actual speedrun routing optimization problem. Different concepts of graph representations are presented and their potential is discussed. Visions both for problem modeling as well as solving are presented and assessed regarding suitability and expected challenges. Finally, a first assessment of the applicability of existing optimization methods to the defined problem is made, including metaheuristics/EA and Deep Learning methods.
Keywords
Cite
@article{arxiv.2106.01182,
title = {Automating Speedrun Routing: Overview and Vision},
author = {Matthias Groß and Dietlind Zühlke and Boris Naujoks},
journal= {arXiv preprint arXiv:2106.01182},
year = {2022}
}
Comments
16 pages. This preprint has not undergone peer review (when applicable) or any post-submission improvements or corrections. The Version of Record of this contribution is published in Applications of Evolutionary Computation, EvoApplications 2022; Lecture Notes in Computer Science, vol 13224, and is available online at https://doi.org/10.1007/978-3-031-02462-7_30