Level QA testing with curiosity-driven AI agents

dc.contributorAalto Universityen
dc.contributorAalto-yliopistofi
dc.contributor.advisorGuckelsberger, Christian
dc.contributor.authorOshiro, Ken
dc.contributor.departmentartmedfi
dc.contributor.schoolTaiteiden ja suunnittelun korkeakoulufi
dc.contributor.schoolSchool of Arts, Design and Architectureen
dc.contributor.supervisorHämäläinen, Perttu
dc.date.accessioned2023-09-03T15:05:48Z
dc.date.available2023-09-03T15:05:48Z
dc.date.issued2023
dc.description.abstractAdvancements in reinforcement learning have allowed agents to play games of increased complexity. One potential use-case of this technology for the game industry would be for QA testing. This thesis investigates the possibility of training an autonomous agent inside a prevalent game engine, Unreal Engine 5.0, to explore a level and detect missing colliders. The focus of this thesis is the study of the performance of a curiosity-driven AI agent. Curiosity allows agents to discover novel game states through intrinsic motivation, without explicitly defined goals. Coupled with a count-based exploration of the game’s level and a visualization of the agent’s path, the solution’s coverage and speed is evaluated. It is compared to a random policy and a human tester. Results indicate that the agent’s coverage is sufficient to explore the whole level. Its performance in finding collision bugs is higher than both a random policy and a human tester.en
dc.format.extent40
dc.format.mimetypeapplication/pdfen
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/123061
dc.identifier.urnURN:NBN:fi:aalto-202309035398
dc.language.isoenen
dc.programmeMaster's Programme in New Mediafi
dc.programme.majorfi
dc.subject.keywordreinforcement learningen
dc.subject.keywordmachine learningen
dc.subject.keywordgame testingen
dc.subject.keywordartificial intelligenceen
dc.subject.keywordUnreal engineen
dc.subject.keywordAIen
dc.titleLevel QA testing with curiosity-driven AI agentsen
dc.typeG2 Pro gradu, diplomityöfi
dc.type.ontasotMaster's thesisen
dc.type.ontasotMaisterin opinnäytefi
local.aalto.electroniconlyyes
local.aalto.openaccessyes
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
master_Oshiro_Ken_2023.pdf
Size:
1.14 MB
Format:
Adobe Portable Document Format