Cooperative AI Course ID 15784 Doctoral Breadth Course: Artificial Intelligence - (-) Classes marked with a "-" (dash) are intended as more advanced topics for CSD doctoral and 5th year master's students in the specific research area. Description In AI and beyond, systems of multiple agents are naturally modeled using game theory. From game theory, we know that sometimes, when each agent pursues its own objectives, the outcome may be one that is bad for all agents (e.g., the Prisoner's Dilemma). Learning algorithms can indeed converge to such bad equilibria. What can be done to prevent such bad outcomes, and how should we think about designing agents in such contexts? In this course, we will approach this question from a variety of angles, ranging from traditional approaches in game theory to novel ones that fit AI better than humans. Key Topics TOPICS TO BE COVERED: Game theory: representations, solution concepts, algorithms Cooperation in repeated games and stochastic games, folk theorems Commitment Program equilibrium Correlated equilibrium, mediated equilibrium Team games Mechanism design Automated mechanism design Learning in games, equilibrium selection Evaluating agents, also in non-zero-sum games Agent design: identities, preferences, beliefs Imperfect recall, belief formation, variants of decision theory Cooperative game theory Required Background Knowledge There is no formal prerequisite for the course, but we do expect students to be mathematically well prepared and ready to undertake a significant course project. For students just looking to gain general background in AI, 15-780 is better suited. Course Relevance Graduate students, well prepared undergrads are welcome Course Goals An introduction to the foundations of the new research area of cooperative AI. Understanding of relevant existing techniques in (algorithmic) game theory; understanding of new techniques for cooperative AI such as program equilibrium, simulation, and decision theory variants; understanding of how to do research in this new area. Learning Resources Materials will be made available on the course website. A text that provides general background in game theory is Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations by Shoham and Leyton-Brown, but this text covers only some of the topics of the course. Assessment Structure Grading will be based on class participation (10%), homework assignments (20%), a midterm exam (20%), and a class project (50%). Extra Time Commitment n/a Course Link https://www.cs.cmu.edu/~15784/
