scientific article; zbMATH DE number 1804105

MaRDI QIDQ3148807zbMATH OpenFDO

Authors A. Piccolboni, Christian Schindelhauer

Publication date 22 September 2002

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/2111/21110208

Mathematics Subject Classification ID

Computational learning theory (68Q32) Applications of game theory (91A80)

Recommendations

• Prediction, Optimization, and Learning in Repeated Games
• Sequential estimation of dynamic discrete games: a comment
• Sequential Estimation of Dynamic Discrete Games
• Estimation of Discrete Games with Weak Assumptions on Information
• Learning and equilibrium as useful approximations: accuracy of prediction on randomly selected constant sum games
• Robust predictions in infinite-horizon games -- an unrefinable folk theorem
• On the iterated estimation of dynamic discrete choice games
• Robust predictions in games with incomplete information

Cited in

(13)

• Improving multi-armed bandit algorithms in online pricing settings
• Randomized prediction of individual sequences
• Counterfactual prediction in complete information games: point prediction under partial identification
• Improved second-order bounds for prediction with expert advice
• A general internal regret-free strategy
• Online learning to rank with top-k feedback
• Learning to optimize via information-directed sampling
• Partial monitoring -- classification, regret bounds, and algorithms
• DOMAIN EXTENSIONS OF THE ERLANG LOSS FUNCTION: THEIR SCALABILITY AND ITS APPLICATIONS TO COOPERATIVE GAMES
• Online prediction
• Best-of-both-worlds algorithms for partial monitoring
• Cleaning up the neighborhood: a full classification for adversarial partial monitoring
• Sensor networks: from dependence analysis via matroid bases to online synthesis

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3148807)