Chasing Ghosts: Competing with Stateful Policies

DOI10.1137/14100227XzbMath1410.91168arXiv1407.7635MaRDI QIDQ2968152

Tomer Koren, Moshe Tennenholtz, Uriel Feige

Publication date: 10 March 2017

Published in: SIAM Journal on Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1407.7635

zbMATH Keywords

online learningsequential decision makingmultiarmed banditbandit feedbackstateful policies

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Decision theory (91B06) Learning and adaptive systems in artificial intelligence (68T05) Probabilistic games; gambling (91A60) Online algorithms; streaming algorithms (68W27)

Related Items (2)

One-Sided Epsilon-Approximants ⋮ Quasi-random words and limits of word sequences

Uses Software

• AdaBoost.MH

Cites Work

• Unnamed Item
• A decision-theoretic generalization of on-line learning and an application to boosting
• Differential privacy under continual observation
• Online Markov Decision Processes Under Bandit Feedback
• Why are Images Smooth?
• Online Markov Decision Processes
• Combining expert advice in reactive environments
• Universal prediction of individual sequences
• How to use expert advice
• On sequential strategies for loss functions with memory
• Universal prediction
• The Nonstochastic Multiarmed Bandit Problem
• Bandits with switching costs
• Algorithmic Game Theory
• Prediction, Learning, and Games
• High-confidence predictions under adversarial uncertainty

This page was built for publication: Chasing Ghosts: Competing with Stateful Policies