Better algorithms for benign bandits

zbMATH Open1425.91084MaRDI QIDQ4633809FDOQ4633809

Authors: Elad Hazan, Satyen Kale 

Publication date: 6 May 2019

Full work available at URL: https://dl.acm.org/citation.cfm?id=1496775

Recommendations

• scientific article; zbMATH DE number 6253908
• Online convex optimization in the bandit setting: gradient descent without a gradient
• The Nonstochastic Multiarmed Bandit Problem
• Efficient algorithms for online decision problems.
• Algorithmic Learning Theory

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Decision theory (91B06) Markov and semi-Markov decision processes (90C40) Probabilistic games; gambling (91A60)

Cited In (7)

• Title not available (Why is that?)
• Extracting certainty from uncertainty: regret bounded by variation in costs
• Algorithms for adversarial bandit problems with multiple plays
• Regret bounded by gradual variation for online convex optimization
• Greedy Algorithm Almost Dominates in Smoothed Contextual Bandits
• Weighted last-step min-max algorithm with improved sub-logarithmic regret
• Learning Theory

This page was built for publication: Better algorithms for benign bandits

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4633809)