Picture for Ioannis Panageas

Ioannis Panageas

Last-iterate Convergence Separation between Extra-gradient and Optimism in Constrained Periodic Games

Add code
Jun 15, 2024
Viaarxiv icon

Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence Beyond the Minty Property

Add code
Dec 21, 2023
Viaarxiv icon

On the Convergence of No-Regret Learning Dynamics in Time-Varying Games

Add code
Jan 26, 2023
Figure 1 for On the Convergence of No-Regret Learning Dynamics in Time-Varying Games
Figure 2 for On the Convergence of No-Regret Learning Dynamics in Time-Varying Games
Figure 3 for On the Convergence of No-Regret Learning Dynamics in Time-Varying Games
Figure 4 for On the Convergence of No-Regret Learning Dynamics in Time-Varying Games
Viaarxiv icon

On Scrambling Phenomena for Randomly Initialized Recurrent Networks

Add code
Oct 11, 2022
Figure 1 for On Scrambling Phenomena for Randomly Initialized Recurrent Networks
Figure 2 for On Scrambling Phenomena for Randomly Initialized Recurrent Networks
Figure 3 for On Scrambling Phenomena for Randomly Initialized Recurrent Networks
Figure 4 for On Scrambling Phenomena for Randomly Initialized Recurrent Networks
Viaarxiv icon

Efficiently Computing Nash Equilibria in Adversarial Team Markov Games

Add code
Aug 03, 2022
Figure 1 for Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
Viaarxiv icon

Accelerated Multiplicative Weights Update Avoids Saddle Points almost always

Add code
Apr 25, 2022
Figure 1 for Accelerated Multiplicative Weights Update Avoids Saddle Points almost always
Figure 2 for Accelerated Multiplicative Weights Update Avoids Saddle Points almost always
Figure 3 for Accelerated Multiplicative Weights Update Avoids Saddle Points almost always
Figure 4 for Accelerated Multiplicative Weights Update Avoids Saddle Points almost always
Viaarxiv icon

Teamwork makes von Neumann work: Min-Max Optimization in Two-Team Zero-Sum Games

Add code
Nov 29, 2021
Figure 1 for Teamwork makes von Neumann work: Min-Max Optimization in Two-Team Zero-Sum Games
Figure 2 for Teamwork makes von Neumann work: Min-Max Optimization in Two-Team Zero-Sum Games
Figure 3 for Teamwork makes von Neumann work: Min-Max Optimization in Two-Team Zero-Sum Games
Figure 4 for Teamwork makes von Neumann work: Min-Max Optimization in Two-Team Zero-Sum Games
Viaarxiv icon

Independent Natural Policy Gradient Always Converges in Markov Potential Games

Add code
Oct 20, 2021
Figure 1 for Independent Natural Policy Gradient Always Converges in Markov Potential Games
Figure 2 for Independent Natural Policy Gradient Always Converges in Markov Potential Games
Figure 3 for Independent Natural Policy Gradient Always Converges in Markov Potential Games
Figure 4 for Independent Natural Policy Gradient Always Converges in Markov Potential Games
Viaarxiv icon

Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games

Add code
Jun 03, 2021
Figure 1 for Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games
Figure 2 for Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games
Figure 3 for Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games
Figure 4 for Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games
Viaarxiv icon

Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev

Add code
Oct 11, 2020
Figure 1 for Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev
Figure 2 for Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev
Figure 3 for Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev
Viaarxiv icon