You are cordially invited to the next WARA Media and Language webinar on June 10, at 15:00-16:00 CEST, where Konrad Tollmar and Linus Gisslén from EA Games will talk about machine learning and AI for video games. As usual, Sandor Albrecht will host the event.
Register via the event’s Lyyti page. Registration closes on 12:00, June 9, and a zoom link will be distributed shortly before the webinar.
Abstract
Game AI is a term that has been around since the beginning of video games in the 1950s. However, these techniques usually deal with pathfinding and decision trees to guide the actions of NPCs. Now we start to see how modern AI and Machine Learning research advances could bring unprecedented benefits to video games and game development.
This talk will give an introduction to current research. We will present applications of state-of-the-art, such as Procedural Content Generation (PCG) to create game content, and Reinforcement Learning (RL) to provide behavior for game avatars. We will also discuss other emerging fields, i.e., Natural Language Processing (NLP) in games.
We will focus on the possibilities and the challenges when applying ML in the game industry and share our experiences in the cross-section between academic research and application
About the speakers
Konrad Tollmar is the Research Director at SEED Electronic Arts and Associate professor at KTH. Since joining EA, he led SEEDs research efforts in Machine Learning. In his role as RD, he is also responsible for partnerships with universities and external research organizations. His key research interest is towards applied AI and building interactive experiences using emerging AI technologies. Prior to EA, he led the Mobile Service Lab at KTH, Associate professor at Ingvar Kamprad Design Centre – Lund University, a Research Scientist at MIT CSAIL, Postdoc at MIT AI-Lab, and Research Scientist at Interactive Institut.
Linus Gisslén is a Senior Research Engineer in Machine Learning at SEED EA. His current research focus is on Reinforcement Learning (RL) and Procedural Generated Content (PCG). He is the project lead on EA’s effort to use machine learning to improve automated testing of games. Previous experience includes a PhD. from TU München, Germany, researcher at Swedish Defence Research Agency (FOI), and a PostDoc position at Jürgen Schmidhuber’s AI lab in Switzerland where the main research focus was on Reinforcement Learning.