no code implementations • 22 Sep 2023 • Derek Yadgaroff, Alessandro Sestini, Konrad Tollmar, Ayca Ozcelikkale, Linus Gisslén
Imitation learning is an effective approach for training game-playing agents and, consequently, for efficient game production.
no code implementations • 15 Aug 2023 • William Ahlberg, Alessandro Sestini, Konrad Tollmar, Linus Gisslén
MultiGAIL is based on generative adversarial imitation learning and uses multiple discriminators as reward models, inferring the environment reward by comparing the agent and distinct expert policies.
no code implementations • 25 Aug 2022 • Matilda Tamm, Olivia Shamon, Hector Anadon Leon, Konrad Tollmar, Linus Gisslén
We report promising results and envision that this method can be used to automate the process of LOD reduction testing and validation.
no code implementations • 15 Aug 2022 • Alessandro Sestini, Joakim Bergdahl, Konrad Tollmar, Andrew D. Bagdanov, Linus Gisslén
In games, as in and many other domains, design validation and testing is a huge challenge as systems are growing in size and manual testing is becoming infeasible.
no code implementations • 21 Feb 2022 • Alessandro Sestini, Linus Gisslén, Joakim Bergdahl, Konrad Tollmar, Andrew D. Bagdanov
This paper proposes a novel deep reinforcement learning algorithm to perform automatic analysis and detection of gameplay issues in complex 3D navigation environments.
no code implementations • 29 Mar 2021 • Joakim Bergdahl, Camilo Gordillo, Konrad Tollmar, Linus Gisslén
General game testing relies on the use of human play testers, play test scripting, and prior knowledge of areas of interest to produce relevant test data.
no code implementations • 25 Mar 2021 • Camilo Gordillo, Joakim Bergdahl, Konrad Tollmar, Linus Gisslén
As modern games continue growing both in size and complexity, it has become more challenging to ensure that all the relevant content is tested and that any potential issue is properly identified and fixed.
no code implementations • 8 Mar 2021 • Linus Gisslén, Andy Eakins, Camilo Gordillo, Joakim Bergdahl, Konrad Tollmar
We present a new approach ARLPCG: Adversarial Reinforcement Learning for Procedural Content Generation, which procedurally generates and tests previously unseen environments with an auxiliary input as a control variable.
no code implementations • 14 Mar 2018 • Jack Harmer, Linus Gisslén, Jorge del Val, Henrik Holst, Joakim Bergdahl, Tom Olsson, Kristoffer Sjöö, Magnus Nordin
This initial training technique kick-starts TD learning and the agent quickly learns to surpass the capabilities of the expert.