Near-optimal no-regret algorithms for zero-sum games

MaRDI QIDQ5365040zbMATH OpenFDO

Authors Constantinos Daskalakis, Alan Deckelbaum, Anthony Kim

Publication date 29 September 2017

Full work available at URL http://dl.acm.org/citation.cfm?id=2133057

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) 2-person games (91A05) Noncooperative games (91A10) Rationality and learning in game theory (91A26) Applications of game theory (91A80)

Recommendations

• Near-optimal no-regret algorithms for zero-sum games
• A general class of no-regret learning algorithms and game-theoretic equilibria.
• Learning, regret minimization, and equilibria
• Learning in games with continuous action sets and unknown payoff functions
• No--regret: a connection between computational learning theory and game theory

Cited in

(11)

• A multiplicative weight updates algorithm for packing and covering semi-infinite linear programs
• Near-optimal no-regret algorithms for zero-sum games
• Generalized mirror descents in congestion games
• First-order algorithm with \({\mathcal{O}(\ln(1/\epsilon))}\) convergence for \({\epsilon}\)-equilibrium in two-person zero-sum games
• No--regret: a connection between computational learning theory and game theory
• A general class of no-regret learning algorithms and game-theoretic equilibria.
• No-regret dynamics in the Fenchel game: a unified framework for algorithmic convex optimization
• No-regret learning for repeated non-cooperative games with lossy bandits
• On the limitations and possibilities of Nash regret minimization in zero-sum matrix games under noisy feedback
• Last round convergence and no-dynamic regret in asymmetric repeated games
• Convergence to equilibrium of no-regret dynamics in congestion games

This page was built for publication: Near-optimal no-regret algorithms for zero-sum games

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5365040)