Alert button
Picture for Georgios Piliouras

Georgios Piliouras

Alert button

States as Strings as Strategies: Steering Language Models with Game-Theoretic Solvers

Add code
Bookmark button
Alert button
Feb 06, 2024
Ian Gemp, Yoram Bachrach, Marc Lanctot, Roma Patel, Vibhavari Dasagi, Luke Marris, Georgios Piliouras, Siqi Liu, Karl Tuyls

Figure 1 for States as Strings as Strategies: Steering Language Models with Game-Theoretic Solvers
Figure 2 for States as Strings as Strategies: Steering Language Models with Game-Theoretic Solvers
Figure 3 for States as Strings as Strategies: Steering Language Models with Game-Theoretic Solvers
Figure 4 for States as Strings as Strategies: Steering Language Models with Game-Theoretic Solvers
Viaarxiv icon

Neural Population Learning beyond Symmetric Zero-sum Games

Add code
Bookmark button
Alert button
Jan 10, 2024
Siqi Liu, Luke Marris, Marc Lanctot, Georgios Piliouras, Joel Z. Leibo, Nicolas Heess

Figure 1 for Neural Population Learning beyond Symmetric Zero-sum Games
Figure 2 for Neural Population Learning beyond Symmetric Zero-sum Games
Figure 3 for Neural Population Learning beyond Symmetric Zero-sum Games
Figure 4 for Neural Population Learning beyond Symmetric Zero-sum Games
Viaarxiv icon

Exploiting hidden structures in non-convex games for convergence to Nash equilibrium

Add code
Bookmark button
Alert button
Dec 27, 2023
Iosif Sakos, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Panayotis Mertikopoulos, Georgios Piliouras

Viaarxiv icon

Scalable AI Safety via Doubly-Efficient Debate

Add code
Bookmark button
Alert button
Nov 23, 2023
Jonah Brown-Cohen, Geoffrey Irving, Georgios Piliouras

Viaarxiv icon

A Quadratic Speedup in Finding Nash Equilibria of Quantum Zero-Sum Games

Add code
Bookmark button
Alert button
Nov 17, 2023
Francisca Vasconcelos, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Panayotis Mertikopoulos, Georgios Piliouras, Michael I. Jordan

Viaarxiv icon

Stability of Multi-Agent Learning: Convergence in Network Games with Many Players

Add code
Bookmark button
Alert button
Jul 26, 2023
Aamal Hussain, Dan Leonte, Francesco Belardinelli, Georgios Piliouras

Figure 1 for Stability of Multi-Agent Learning: Convergence in Network Games with Many Players
Figure 2 for Stability of Multi-Agent Learning: Convergence in Network Games with Many Players
Figure 3 for Stability of Multi-Agent Learning: Convergence in Network Games with Many Players
Figure 4 for Stability of Multi-Agent Learning: Convergence in Network Games with Many Players
Viaarxiv icon

Discovering How Agents Learn Using Few Data

Add code
Bookmark button
Alert button
Jul 13, 2023
Iosif Sakos, Antonios Varvitsiotis, Georgios Piliouras

Figure 1 for Discovering How Agents Learn Using Few Data
Figure 2 for Discovering How Agents Learn Using Few Data
Figure 3 for Discovering How Agents Learn Using Few Data
Figure 4 for Discovering How Agents Learn Using Few Data
Viaarxiv icon

Multiplicative Updates for Online Convex Optimization over Symmetric Cones

Add code
Bookmark button
Alert button
Jul 06, 2023
Ilayda Canyakmaz, Wayne Lin, Georgios Piliouras, Antonios Varvitsiotis

Figure 1 for Multiplicative Updates for Online Convex Optimization over Symmetric Cones
Figure 2 for Multiplicative Updates for Online Convex Optimization over Symmetric Cones
Figure 3 for Multiplicative Updates for Online Convex Optimization over Symmetric Cones
Figure 4 for Multiplicative Updates for Online Convex Optimization over Symmetric Cones
Viaarxiv icon

Chaos persists in large-scale multi-agent learning despite adaptive learning rates

Add code
Bookmark button
Alert button
Jun 01, 2023
Emmanouil-Vasileios Vlatakis-Gkaragkounis, Lampros Flokas, Georgios Piliouras

Figure 1 for Chaos persists in large-scale multi-agent learning despite adaptive learning rates
Figure 2 for Chaos persists in large-scale multi-agent learning despite adaptive learning rates
Figure 3 for Chaos persists in large-scale multi-agent learning despite adaptive learning rates
Figure 4 for Chaos persists in large-scale multi-agent learning despite adaptive learning rates
Viaarxiv icon

Asymptotic Convergence and Performance of Multi-Agent Q-Learning Dynamics

Add code
Bookmark button
Alert button
Jan 23, 2023
Aamal Abbas Hussain, Francesco Belardinelli, Georgios Piliouras

Figure 1 for Asymptotic Convergence and Performance of Multi-Agent Q-Learning Dynamics
Figure 2 for Asymptotic Convergence and Performance of Multi-Agent Q-Learning Dynamics
Viaarxiv icon