Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games
Department: Computer Science
Quarter: Spring 2021
Seminar Date: May 28, 2021
Speaker Name:
Ioannis Panageas
Ioannis Panageas
Organization:
UC Irvine
UC Irvine
Start Time:
End Time:
Speaker Website:
https://panageas.github.io/
https://panageas.github.io/
Bio:
Ioannis is an Assistant Professor of Computer Science at UCI. He is interested in the theory of computation, machine learning and its interface with non-convex optimization, dynamical systems, probab…
Ioannis is an Assistant Professor of Computer Science at UCI. He is interested in the theory of computation, machine learning and its interface with non-convex optimization, dynamical systems, probab…
Photo Link:
Summary:
Potential games are arguably one of the most important and widely studied classes of normal form games. They define the archetypal setting of multi-agent coordination as all agent utilities are perfe…
Potential games are arguably one of the most important and widely studied classes of normal form games. They define the archetypal setting of multi-agent coordination as all agent utilities are perfe…
Notes:
Host:
Sameer Singh
Sameer Singh
Host Notes:
Alt Text:
Video: https://youtu.be/d1QRdQ2ayNA