No--regret: a connection between computational learning theory and game theory

DOI10.1007/978-94-007-0714-6_7zbMATH Open1320.91031OpenAlexW137245701MaRDI QIDQ5261296FDOQ5261296

Authors: Amy Greenwald, Amir Jafari, Casey Marks 

Publication date: 3 July 2015

Published in: Games, Norms and Reasons (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-94-007-0714-6_7

Recommendations

• A general class of no-regret learning algorithms and game-theoretic equilibria.
• Learning, regret minimization, and equilibria
• No regrets about no-regret
• Near-optimal no-regret algorithms for zero-sum games
• Near-optimal no-regret algorithms for zero-sum games

Mathematics Subject Classification ID

Computational learning theory (68Q32) Multistage and repeated games (91A20) Rationality and learning in game theory (91A26)

Cited In (6)

• Verified learning without regret. From algorithmic game theory to distributed systems with mechanized complexity guarantees
• Near-optimal no-regret algorithms for zero-sum games
• No regrets about no-regret
• A general class of no-regret learning algorithms and game-theoretic equilibria.
• Near-optimal no-regret algorithms for zero-sum games
• Hedging under uncertainty: regret minimization meets exponentially fast convergence

This page was built for publication: No-\(\Phi\)-regret: a connection between computational learning theory and game theory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5261296)