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 …
of Online Convex Optimization. Here, online learning refers to the framework of regret …
Near-optimal no-regret learning in general games
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 …
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
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 …
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
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 …
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
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 …
which is often modeled as a constrained saddle-point optimization problem with probability …
Linear last-iterate convergence in constrained saddle-point optimization
Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative Weights Update
(OMWU) for saddle-point optimization have received growing attention due to their favorable …
(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 …
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
We study the problem of computing an optimal policy of an infinite-horizon discounted
constrained Markov decision process (constrained MDP). Despite the popularity of …
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
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 …
doing so comes at the cost of an exponential blowup of the strategy space. So, progress on …
Last-iterate convergence in extensive-form games
Regret-based algorithms are highly efficient at finding approximate Nash equilibria in
sequential games such as poker games. However, most regret-based algorithms, including …
sequential games such as poker games. However, most regret-based algorithms, including …