An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regret.

Matthew Jones Huy Le Nguyen Thy D. Nguyen

Published in: CoRR (2022)

Keyphrases

multi armed bandit
multi agent
k means
worst case
optimal solution
probabilistic model
online learning
similarity measure
objective function
reinforcement learning
computational complexity
expectation maximization
regret minimization
multi armed bandits