Contextual bandits with concave rewards, and an application to fair ranking.

Virginie Do Elvis Dohmatob Matteo Pirotta Alessandro Lazaric Nicolas Usunier

Published in: CoRR (2022)

Keyphrases

ranked list
multi armed bandits
contextual information
rank aggregation
reinforcement learning
evaluation measures
objective function
rank order
bandit problems
markov decision processes
piecewise linear
ranking algorithm
ranking functions
user feedback