YoVDO

Connections between POMDPs and Partially Observed N-Player Mean-Field Games

Offered By: GERAD Research Center via YouTube

Tags

Mean-Field Games Courses Game Theory Courses Markov Decision Processes Courses Decision Theory Courses Multi-Agent Systems Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the intricate connections between Partially Observable Markov Decision Processes (POMDPs) and partially observed n-player mean-field games in this 58-minute seminar presented by Bora Yongacoglu from the University of Toronto. Delve into a discrete-time model of mean-field games with finite players and partial global state observability, focusing on settings with mean-field observability. Discover how symmetric stationary memoryless policies of counterparts lead to a fully observed, time-homogenous MDP for a given agent, and learn about the existence of memoryless, stationary perfect equilibrium in n-player games with mean-field observability. Examine the limitations of relaxing the symmetry condition through examples, and explore scenarios with narrower observation channels where agents face POMDPs instead of MDPs, even with symmetric policies from counterparts.

Syllabus

Connections between POMDPs and partially observed n-player mean-field games, Bora Yongacoglu


Taught by

GERAD Research Center

Related Courses

Stanford Seminar - Failures & Where to Find Them: Considering Safety as a Function of Structure
Stanford University via YouTube
Modeling Conceptual Understanding in Image Reference Games - CVPR 2020 Tutorial
Bolei Zhou via YouTube
Multi-Agent Reinforcement Learning - Part II
Simons Institute via YouTube
AI- From Algorithms to Ethics - ACM WomENcourage 2020
Association for Computing Machinery (ACM) via YouTube
Python Reinforcement Learning using OpenAI Gymnasium – Full Course
freeCodeCamp