The Thesis Review [05] Julian Togelius - Computational Intelligence and Games
Aug 14, 2020
Julian Togelius, an Associate Professor at NYU and co-director of the Game Innovation Lab, dives into the exciting world of AI in gaming. He discusses how video games serve as a testing ground for AI techniques and the evolution of intelligent behaviors in NPCs. Togelius highlights the significance of procedural content generation and its role in enhancing AI capabilities. He also shares insights on unconventional research paths, training AI in racing games, and the intricacies of neural networks, all while driving innovation in game design.
AI Snips
Chapters
Books
Transcript
Episode notes
Complexity of General Intelligence
- Intelligence is a complex mix of different cognitive capacities without a single general intelligence.
- We lack understanding to define or build a truly general intelligence system today.
From Philosophy to Games AI
- Julian Togelius started with philosophy and psychology but moved to computer science due to impatience with slow progress.
- Early robotics work was slow and tedious, prompting a shift to using games as a test bed instead.
AI for Games vs Games for AI
- Video games offer unique cognitive challenges that differ from classical board games like chess.
- AI for games and games as testbeds for AI are connected but involve different goals and methods.
