Ambiguity aversion in multi-armed bandit problems

DOI10.1007/s11238-011-9259-2zbMath1274.91110OpenAlexW2058587255MaRDI QIDQ656883

Christopher M. Anderson

Publication date: 13 January 2012

Published in: Theory and Decision (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11238-011-9259-2

zbMATH Keywords

Gittins indexambiguity aversionbandit problem

Mathematics Subject Classification ID

Bayesian problems; characterization of Bayes procedures (62C10) Markov and semi-Markov decision processes (90C40) Statistical methods; economic indices and measures (91B82) Probabilistic games; gambling (91A60) Experimental studies (91A90)

Related Items (5)

Robust experimentation in the continuous time bandit problem ⋮ Nonparametric learning rules from bandit experiments: the eyes have it! ⋮ The K-armed bandit problem with multiple priors ⋮ Capacity expansion under uncertainty in an oligopoly using indirect reinforcement-learning ⋮ Learning and self-confirming long-run biases

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Recursive smooth ambiguity preferences
• A Bayesian analysis of human decision-making on bandit problems
• Maxmin expected utility with non-unique prior
• Recent developments in modeling preferences: Uncertainty and ambiguity
• An experimental analysis of the bandit problem
• Good news and bad news: Search from unknown wage offer distributions
• Risk, Ambiguity, and the Savage Axioms
• Price Differences in Almost Competitive Markets
• The Ellsberg Paradox and Risk Aversion: An Anticipated Utility Approach
• Subjective Probability and Expected Utility without Additivity
• Sequential Choice Under Ambiguity: Intuitive Solutions to the Armed-Bandit Problem
• Ellsberg Revisited: An Experimental Study
• A Definition of Subjective Probability

This page was built for publication: Ambiguity aversion in multi-armed bandit problems