Nearly Minimax-Optimal Regret for Linearly Parameterized Bandits.

Yingkai Li Yining Wang Yuan Zhou

Published in: IEEE Trans. Inf. Theory (2024)

Keyphrases

worst case
regret bounds
minimax regret
multi armed bandit
lower bound
neural network
optimal solution
dynamic programming
online learning
computational complexity
upper bound
closed form
optimal design
asymptotically optimal