A new Google patent details an AI-based gaming system that aims to automate the process of game testing and QA. As numerous videogame QA teams around the world continue to unionise in order to protect their rights, one of the biggest and most valuable companies appears to be angling for a way to automate more of the videogame QA process.
According to Google’s patent, the number of issues found in games at launch is the fault of testing teams unable to handle the size and scope of modern games. “Game testing is a predominantly manual process, highly dependent on humans who repeatedly play the game and look for defects,” the patent reads. “Unfortunately these teams are no longer able to scale with the complexity of modern games, leading to delayed launches and lower quality products.”
Google claims that its new “Gameplay Trainer system provides game developers with a solution that is useful, flexible, trainable, and able to progress towards objectives more than simply ‘winning’ in a game application.” That’s important because testers often look for issues that arise as a result of unusual ways of playing, so a system that simply determined the optimal way to succeed in-game would likely miss such problems.
Continuing, the patent (via Very Ali Gaming) describes how the systems can be trained to execute gameplay actions in real-time, generating observational data and using this to improve its future actions and adjust as needed for further testing. Much like other artificial intelligence and machine learning tools, Google proposes that its gameplay trainer will continue to improve as it spends more time testing a given game.
This patent comes after QA teams at several large companies have formed unions, with tester teams at
Read more on pcgamesn.com