A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
Weighted Bandits or: How Bandits Learn Distorted Values That Are Not Expected
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Motivated by models of human decision making proposed to explain commonly observed deviations from conventional expected value preferences, we formulate two stochastic multi-armed bandit problems with distorted probabilities on the cost distributions: the classic K-armed bandit and the linearly parameterized bandit. In both settings, we propose algorithms that are inspired by Upper Confidence Bound (UCB) algorithms, incorporate cost distortions, and exhibit sublinear regret assuming Holderdoi:10.1609/aaai.v31i1.10922 fatcat:tls2d3ay4rejxdkhfia5g2sptq