Recent years have witnessed significant advances in reinforcement learning (RL), which
has registered tremendous success in solving various sequential decision-making problems …

Recent applications that arise in machine learning have surged significant interest in solving
min-max saddle point games. This problem has been extensively studied in the convex …

In general-sum games the interaction of self-interested learning agents commonly leads to
collectively worst-case outcomes, such as defect-defect in the iterated prisoner's dilemma …

This work studies an algorithm, which we call magnetic mirror descent, that is inspired by
mirror descent and the non-Euclidean proximal gradient algorithm. Our contribution is …

Training generative adversarial networks requires balancing of delicate adversarial
dynamics. Even with careful tuning, training may diverge or end up in a bad equilibrium with …

Learning in general-sum games is unstable and frequently leads to socially undesirable
(Pareto-dominated) outcomes. To mitigate this, Learning with Opponent-Learning …

We introduce a new algorithm for the numerical computation of Nash equilibria of
competitive two-player games. Our method is a natural generalization of gradient descent to …

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 …

Smooth minimax games often proceed by simultaneous or alternating gradient updates.
Although algorithms with alternating updates are commonly used in practice, the majority of …

The past few years have witnessed an increased interest in learning Hamiltonian dynamics
in deep learning frameworks. As an inductive bias based on physical laws, Hamiltonian …