Multi-agent performative prediction: From global stability and optimality to chaos

G Piliouras, FY Yu - Proceedings of the 24th ACM Conference on …, 2023 - dl.acm.org
The recent framework of performative prediction [Perdomo et al. 2020] is aimed at capturing
settings where predictions influence the outcome they want to predict. In this paper, we …

Vortices instead of equilibria in minmax optimization: Chaos and butterfly effects of online learning in zero-sum games

YK Cheung, G Piliouras - Conference on Learning Theory, 2019 - proceedings.mlr.press
We establish that algorithmic experiments in zero-sum games “fail miserably” to confirm the
unique, sharp prediction of maxmin equilibration. Contradicting nearly a century of economic …

Chaos, extremism and optimism: Volume analysis of learning in games

YK Cheung, G Piliouras - Advances in Neural Information …, 2020 - proceedings.neurips.cc
We perform volume analysis of Multiplicative Weights Updates (MWU) and its optimistic
variant (OMWU) in zero-sum as well as coordination games. Our analysis provides new …

Learning in matrix games can be arbitrarily complex

GP Andrade, R Frongillo… - Conference on Learning …, 2021 - proceedings.mlr.press
Many multi-agent systems with strategic interactions have their desired functionality
encoded as the Nash equilibrium of a game, eg machine learning architectures such as …

Matrix multiplicative weights updates in quantum zero-sum games: Conservation laws & recurrence

R Jain, G Piliouras, R Sim - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Recent advances in quantum computing and in particular, the introduction of quantum
GANs, have led to increased interest in quantum zero-sum game theory, extending the …

The dynamics of q-learning in population games: A physics-inspired continuity equation model

S Hu, CW Leung, H Leung, H Soh - ar** a dynamical model for learning in games has attracted much recent interest. In
stochastic games, agents need to make decisions in multiple states, and transitions between …

Online learning in periodic zero-sum games

T Fiez, R Sim, S Skoulakis… - Advances in Neural …, 2021 - proceedings.neurips.cc
A seminal result in game theory is von Neumann's minmax theorem, which states that zero-
sum games admit an essentially unique equilibrium solution. Classical learning results build …

Hypergraph-Based Model for Modelling Multi-agent Q-Learning Dynamics in Public Goods Games

J Shi, C Liu, J Liu - IEEE Transactions on Network Science and …, 2024 - ieeexplore.ieee.org
Modeling the learning dynamic of multi-agent systems has long been a crucial issue for
understanding the emergence of collective behavior. In public goods games, agents interact …