Potential-based algorithms in online prediction and game theory

DOI10.1007/3-540-44581-1_4MaRDI QIDQ3148799zbMATH OpenFDO

Authors Nicolò Cesa-Bianchi, Gábor Lugosi

Publication date 22 September 2002

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/2111/21110048

zbMATH Keywords

Blackwell's strategyboostinginternal regreton-line learningperceptron algorithmuniversal predictionweighted average predictors

Mathematics Subject Classification ID

Computational learning theory (68Q32) Decision theory for games (91A35)

Recommendations

• Potential-based algorithms in on-line prediction and game theory
• Prediction, Learning, and Games
• Learning Theory
• From external to internal regret
• Adaptive game playing using multiplicative weights

Cited in

(7)

• Potential-based algorithms in on-line prediction and game theory
• Adaptive game playing using multiplicative weights
• Online calibrated forecasts: memory efficiency versus universality for learning in games
• Algorithmic Learning Theory
• Online prediction
• Drifting games
• Replicator dynamics: old and new

This page was built for publication: Potential-based algorithms in online prediction and game theory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3148799)