![Ioannis PANAGEAS | Professor | University of California, Irvine, CA | UCI | Department of Computer Science Ioannis PANAGEAS | Professor | University of California, Irvine, CA | UCI | Department of Computer Science](https://www.researchgate.net/publication/355495192/figure/fig1/AS:1082719979216897@1635151967911/Two-different-configurations-of-the-stochastic-congestion-game-on-6-vertices-These_Q320.jpg)
Ioannis PANAGEAS | Professor | University of California, Irvine, CA | UCI | Department of Computer Science
![Ioannis Panagea (Massachusetts Institute of Technology) – Optimization and Multiplicative Weights Update Algorithm under the Lens of Dynamical Systems | Singapore University of Technology and Design (SUTD) Ioannis Panagea (Massachusetts Institute of Technology) – Optimization and Multiplicative Weights Update Algorithm under the Lens of Dynamical Systems | Singapore University of Technology and Design (SUTD)](https://academics.sutd.edu.sg/wp-content/uploads/081117-Seminar-Ioannis-Panageas.jpg)
Ioannis Panagea (Massachusetts Institute of Technology) – Optimization and Multiplicative Weights Update Algorithm under the Lens of Dynamical Systems | Singapore University of Technology and Design (SUTD)
![Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games with Ioannis Panageas - YouTube Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games with Ioannis Panageas - YouTube](https://i.ytimg.com/vi/d1QRdQ2ayNA/mqdefault.jpg)
Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games with Ioannis Panageas - YouTube
![Ioannis PANAGEAS | Professor | University of California, Irvine, CA | UCI | Department of Computer Science Ioannis PANAGEAS | Professor | University of California, Irvine, CA | UCI | Department of Computer Science](https://www.researchgate.net/publication/356027045/figure/fig1/AS:1088226160844802@1636464743766/GDA-OGDA-EG-fail-to-converge-to-a-Nash-Equilibrium-even-in-average_Q320.jpg)