Skip to content
AI News HubLIVE
More
Summary only

Games people — and machines — play: Untangling strategic reasoning to advance AI

Assistant Professor Gabriele Farina mines the foundations of decision-making in complex multi-agent scenarios, combining game theory with machine learning to develop AI that can bluff and negotiate, and achieving superhuman performance in Stratego at minimal cost.

SourceMIT News AIAuthor: Michaela Jarvis | MIT Laboratory for Information and Decision Systems
Games people — and machines — play: Untangling strategic reasoning to advance AI
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Farina's early fascination with machines outperforming humans led him to game theory and AI.
  • He co-developed Cicero, an AI that excels at negotiation and deception in games.
  • His team created a low-cost algorithm that beat the world's best Stratego player.
  • Farina focuses on efficient computation of equilibria in large multi-agent systems.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Agents