发帖
雷达卡
Achieving Near Instance-Optimality and Minimax-Optimality
in Stochastic and Adversarial Linear Bandits Simultaneously
Chung-Wei Lee 1 Haipeng Luo 1 Chen-Yu Wei 1 Mengxiao Zhang 1 Xiaojin Zhang 2
Abstract adversarial environment, the loss vector can be arbitrary in
In this work, we develop linear bandit algorithms each round,√and we are interested in minimax-optimal regret
that automatically adapt to different environments. b ...
京公网安备 11010802022788号
