On minimaxity of follow the leader strategy in the stochastic setting

DOI10.1016/J.TCS.2017.12.030MaRDI QIDQ1663642zbMATH OpenOpenAlexFDO

Authors Wojciech Kotłowski

Publication date 22 August 2018

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.tcs.2017.12.030

zbMATH Keywords

riskexponential familiesonline learningminimax algorithmregretprediction with expert advicepseudo-regretstochastic datafollow the leader

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Inference from stochastic processes and prediction (62M20) Minimax procedures in statistical decision theory (62C20) Rationality and learning in game theory (91A26)

Recommendations

• On minimaxity of follow the leader strategy in the stochastic setting
• Mini-max incentive strategy for leader-follower games under uncertain dynamics
• Optimal incentive strategy for leader-follower games
• Algorithmic Learning Theory
• A Leader-Follower Stochastic Linear Quadratic Differential Game
• Leader-follower stochastic differential game with asymmetric information and applications
• A mean-field linear-quadratic stochastic Stackelberg differential game with one leader and two followers
• On Stackelberg leader with min-max followers to solve fuzzy continuous static games
• A leader-follower partially observed, multiobjective Markov game
• Stackelberg strategies for stochastic systems with multiple followers

Cites work

• scientific article; zbMATH DE number 3602484 (Why is no real title available?)
• scientific article; zbMATH DE number 893887 (Why is no real title available?)
• scientific article; zbMATH DE number 3246773 (Why is no real title available?)
• A decision-theoretic generalization of on-line learning and an application to boosting
• A game of prediction with expert advice
• Efficient algorithms for online decision problems
• Follow the leader if you can, hedge if you must
• How to use expert advice
• On minimaxity of follow the leader strategy in the stochastic setting
• Prediction, Learning, and Games
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• Statistical decision theory and Bayesian analysis. 2nd ed
• The weighted majority algorithm

Cited in

(4)

• Relaxing the i.i.d. assumption: adaptively minimax optimal regret via root-entropic regularization
• Learning Theory
• Follow the leader if you can, hedge if you must
• On minimaxity of follow the leader strategy in the stochastic setting

Describes a project that uses

Uses Software

• AdaBoost.MH

This page was built for publication: On minimaxity of follow the leader strategy in the stochastic setting

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1663642)