AAAI 2015 tutorial SP1: Computing Game-Theoretic Solutions
Sunday, January 25, 2PM-6PM
Vincent Conitzer

Game theory concerns how to form beliefs and act in settings with multiple self-interested agents. The best-known solution concept in game theory is that of Nash equilibrium. But there are also others, such as correlated equilibrium and Stackelberg mixed strategies. The latter concept offers a number of conceptual and computational advantages and has recently been deployed in a number of real-world security domains. I will review these concepts as well as algorithms for computing their solutions. I will also discuss learning in games. No previous background in game theory will be required.

Topics to be covered:

• Introduction to game theory (from CS/AI perspective)
• Representing games
• Standard solution concepts
• (Iterated) dominance
• Minimax strategies
• Nash and correlated equilibrium
• Recent developments
• Commitment: Stackelberg mixed strategies
• Security applications
• Learning in games (time permitting)
• Simple algorithms
• Evolutionary game theory
• Learning in Stackelberg games

Slides:
pptx, pdf.