The Number One Educational Resource for the Game Industry
-
Overview:
-
Alexandre and Piermaria present new research on SIMA (Scalable Instructable Multiworld Agent), an AI agent that follows natural-language instructions to perform tasks across diverse video game environments. Video games are a key proving ground for artificial intelligence (AI) systems. They offer rich learning environments, mirroring real-world complexities with responsive, real-time settings and dynamic objectives. From our early work with Atari games to AlphaStar, which achieved human-grandmaster level in StarCraft II, Google DeepMind has a long history in AI and games. SIMA represents a significant advancement, shifting focus from individual games to a general, instructable game-playing AI. This generalist agent for 3D virtual settings was trained in partnership with game developers across a diverse range of video games. This marks the first instance of an agent demonstrating comprehension of a broad spectrum of gaming worlds, executing tasks via natural-language instructions like a human player. In this talk, Alexandre Moufarek, Google DeepMind's AI Research Group Product Manager and former Game Producer, together with Piermaria Mendolicchio, Senior Technical Program Manager and former Game Compliance Manager, will discuss the history of games and AI research, the SIMA research project's journey, including challenges, learnings, and future research directions.
Recommended
