Super Data Science: ML & AI Podcast with Jon Krohn cover image

663: Astonishing CICERO negotiates and builds trust with humans using natural language

Super Data Science: ML & AI Podcast with Jon Krohn

00:00

Strategic Gameplay and Human Behavior in Board Games

The chapter delves into a game called France vs. Austria, discussing how a bot is trained through self-play reinforcement learning to compete against human players. It explores the influence of trust, cooperation, and human norms in strategic board games like Diplomacy and Settlers of Catan, comparing human strategies with bot strategies that prioritize scores over personal feelings. The speakers emphasize the significance of training AI models on human behavior data to better predict outcomes and decisions in complex games involving alliances, betrayals, and self-interest.

Play episode from 15:41
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app