A modern introduction to online learning

F Orabona - arxiv preprint arxiv:1912.13213, 2019 - arxiv.org
In this monograph, I introduce the basic concepts of Online Learning through a modern view
of Online Convex Optimization. Here, online learning refers to the framework of regret …

Near-optimal no-regret learning in general games

C Daskalakis, M Fishelson… - Advances in Neural …, 2021 - proceedings.neurips.cc
Abstract We show that Optimistic Hedge--a common variant of multiplicative-weights-
updates with recency bias--attains ${\rm poly}(\log T) $ regret in multi-player general-sum …

Finite-time last-iterate convergence for learning in multi-player games

Y Cai, A Oikonomou, W Zheng - Advances in Neural …, 2022 - proceedings.neurips.cc
We study the question of last-iterate convergence rate of the extragradient algorithm by
Korpelevich [1976] and the optimistic gradient algorithm by Popov [1980] in multi-player …

Tight last-iterate convergence rates for no-regret learning in multi-player games

N Golowich, S Pattathil… - Advances in neural …, 2020 - proceedings.neurips.cc
We study the question of obtaining last-iterate convergence rates for no-regret learning
algorithms in multi-player games. We show that the optimistic gradient (OG) algorithm with a …

Fast policy extragradient methods for competitive games with entropy regularization

S Cen, Y Wei, Y Chi - Advances in Neural Information …, 2021 - proceedings.neurips.cc
This paper investigates the problem of computing the equilibrium of competitive games,
which is often modeled as a constrained saddle-point optimization problem with probability …

Linear last-iterate convergence in constrained saddle-point optimization

CY Wei, CW Lee, M Zhang, H Luo - arxiv preprint arxiv:2006.09517, 2020 - arxiv.org
Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative Weights Update
(OMWU) for saddle-point optimization have received growing attention due to their favorable …

Learning in games: a systematic review

RJ Qin, Y Yu - Science China Information Sciences, 2024 - Springer
Game theory studies the mathematical models for self-interested individuals. Nash
equilibrium is arguably the most central solution in game theory. While finding the Nash …

Last-iterate convergent policy gradient primal-dual methods for constrained mdps

D Ding, CY Wei, K Zhang… - Advances in Neural …, 2024 - proceedings.neurips.cc
We study the problem of computing an optimal policy of an infinite-horizon discounted
constrained Markov decision process (constrained MDP). Despite the popularity of …

Kernelized multiplicative weights for 0/1-polyhedral games: Bridging the gap between learning in extensive-form and normal-form games

G Farina, CW Lee, H Luo… - … Conference on Machine …, 2022 - proceedings.mlr.press
While extensive-form games (EFGs) can be converted into normal-form games (NFGs),
doing so comes at the cost of an exponential blowup of the strategy space. So, progress on …

Last-iterate convergence in extensive-form games

CW Lee, C Kroer, H Luo - Advances in Neural Information …, 2021 - proceedings.neurips.cc
Regret-based algorithms are highly efficient at finding approximate Nash equilibria in
sequential games such as poker games. However, most regret-based algorithms, including …