Generative adversarial networks (GANs) represent a zero-sum game between two machine
players, a generator and a discriminator, designed to learn the distribution of data. While …

Compared to minimization, the min-max optimization in machine learning applications is
considerably more convoluted because of the existence of cycles and similar phenomena …

Much recent research effort has been directed to the development of efficient algorithms for
solving minimax problems with theoretical convergence guarantees due to the relevance of …

Owing to their stability and convergence speed, extragradient methods have become a
staple for solving large-scale saddle-point problems in machine learning. The basic premise …

In many practical applications, such as poker, chess, drug interdiction, cybersecurity, and
national defense, players often have adversarial stances, ie, the selfish actions of each …

The hierarchical interaction between the actor and critic in actor-critic based reinforcement
learning algorithms naturally lends itself to a game-theoretic interpretation. We adopt this …

Direct policy search serves as one of the workhorses in modern reinforcement learning (RL),
and its applications in continuous control tasks have recently attracted increasing attention …

We present a new family of min-max optimization algorithms that automatically exploit the
geometry of the gradient data observed at earlier iterations to perform more informative extra …

Multi-agent interactions are increasingly important in the context of reinforcement learning,
and the theoretical foundations of policy gradient methods have attracted surging research …

Understanding the behavior of no-regret dynamics in general N-player games is a
fundamental question in online learning and game theory. A folk result in the field states that …