Work

We Call This Controller Skip:AI for Speedrunning. In Experimental AI in Games (EXAG)

Year: 2025

Type: conference-paper

Abstract: Speedrunning, a community centred around the practice of playing games as fast as possible and often underconstraints, is a rich and vibrant part of modern games culture. It is also an area largely untouched by game AIresearch, despite it having its own culture of technical innovation and research. In this paper, we provide anoverview of modern speedrunning, describe research areas already pursued by the community, and report onexploratory work investigating how AI research might be applied to simple speedrunning processes. We close bysuggesting new research questions this space reveals for us, and suggesting ways that we can peacefully andrespectfully work alongside and as a part of the speedrunning community

Source: University of Southern Denmark Research Portal (University of Southern Denmark)

Authors: Cook, M, Charity, M, Awiszus, M, Carnovalini, F, Dockhorn, Alexander; id_orcid 0000-0001-8711-7428

Language: English

Topic: Artificial Intelligence in Games

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: European Commission, Research Executive Agency

Awards: G1101737611, G3827137662, G8347913318

OpenAlex ID: W7126840806

FWCI:

Cites:

Cited by:

Related to: