YoVDO

Analysis of Mean-Field Games - Lecture 1

Offered By: International Centre for Theoretical Sciences via YouTube

Tags

Game Theory Courses Nash Equilibrium Courses Mean-Field Games Courses Wasserstein Distances Courses

Course Description

Overview

Explore the foundations of mean-field games in this comprehensive lecture from the "Advances in Applied Probability" program at ICTS Bangalore. Delve into static mean-field games, starting with motivations and context before examining abstract frameworks, Nash equilibria, and symmetric games. Learn about convergence questions, p-Wasserstein distance, and asymptotic approximations. Investigate mean-field equilibria, including uniqueness, potential games, and existence proofs. Gain insights into large-scale systems modeling and analysis through probabilistic methods, essential for understanding complex interconnected networks in technology, commerce, and beyond.

Syllabus

Mean-Field Games Lecture 1: Static Mean-Field Games
Motivation and Context of Mean-Field Games
Static Games
Static Games: A Motivating Example
Static Games: Abstract Framework
Nash Equilibria
Symmetric Games
Static Game: Large Symmetric Games
Convergence Questions
p-Wasserstein distance
Static Game: An Asymptotic Approximation
Proof of Convergence Theorem
Static Games: Mean-field Equilibrium
Uniqueness of Mean-Field Equilibria
Potential Games
A Converse to the Limit Theorem
Existence of Mean-Field Equilibria
Proof: A Converse to the Limit Theorem
Next Define the Random Variable


Taught by

International Centre for Theoretical Sciences

Related Courses

Optimal Transport for Inverse Problems and Implicit Regularization
Society for Industrial and Applied Mathematics via YouTube
Universality of Persistence Diagrams and Bottleneck & Wasserstein Distances
Applied Algebraic Topology Network via YouTube
Convergence of Denoising Diffusion Models Under the Manifold Hypothesis
Alan Turing Institute via YouTube
Wasserstein Distributionally Robust Optimization - Theory and Applications in Machine Learning
Institute for Pure & Applied Mathematics (IPAM) via YouTube
DeepParticle: Learning Invariant Measure by Deep Neural Network Minimizing Wasserstein Distance
Inside Livermore Lab via YouTube