[Online Talk] AI Plays Video Games, So Why Not Test Them Too?

Note: we are using this talk for fund-raising for the Meetup group to cover expenses, hence it is a paid event. Tickets are at $3 (only 30!) and $5 (40 tickets). All attendees will get a link to the recording of the talk. Payment and tickets at the Eventbrite site: https://www.eventbrite.com/e/online-talk-ai-plays-video-games-so-why-not-test-them-too-tickets-144028927399

Talk description:
Testing video games is no small feat! Modern video games are highly visual, graphical, customizable, updatable, streamable, and cross-platform compatible. Video game testers are tasked with covering multiple dimensions of an uncountably infinite state space in a constantly evolving application. These dimensions include testing the functionality of the gaming application itself, visual aesthetics of graphics and animations, audio verification of sound effects and music, and trying to break the gameplay mechanics. Furthermore, many video games have an embedded game store that allows players to purchase add-ons in the form of downloadable content. As a result, in-game purchases and subscriptions now represent a key value stream for game developers that needs to be adequately tested to avoid losses in revenue and profits.

AI has been testing games for as long as we can probably remember, so why not have it test them too? For years, researchers and practitioners have been leveraging AI and machine learning to train bots to play games beyond human expert levels. Is it really too far-fetched to think that we can extend their work for the good of software testing? Join Tariq King as he describes how computer vision, reinforcement learning, and autonomous testing can be combined to automatically verify expected behaviors in modern video games. Tariq literally takes automatic test generation, visual validation, and test execution to new levels as he seeks to not only apply this technology to all games, but make it an integral part of game development platforms.

Speaker Bio:
Tariq King is the Chief Scientist at test.ai, where he leads research and development of their core platform for AI-driven testing. Tariq has over fifteen years' experience in software engineering and testing and has formerly held positions as Head of Quality, Director of Quality Engineering, Manager of Software Engineering and Test Architect. Tariq holds Ph.D. and M.S. degrees in Computer Science from Florida International University, and a B.S. in Computer Science from Florida Tech. His areas of research are software testing, artificial intelligence, autonomic and cloud computing, model-driven engineering, and computer science education. He has published over 40 research articles in peer-reviewed IEEE and ACM journals, conferences, and workshops, and has been an international keynote speaker at leading software conferences in industry and academia. He is the co-founder of the Artificial Intelligence for Software Testing Association (AISTA) and has contributed multiple projects to the open-source community.