20 citations · 20 across the 1 of their papers we have counts for
2 papers
cs.LG2018
UCBoost: A Boosting Approach to Tame Complexity and Optimality for Stochastic Bandits
Fang Liu, Sinong Wang, Swapna Buccapatnam +1
In this work, we address the open problem of finding low-complexity near-optimal multi-armed bandit algorithms for sequential decision making problems. Existing bandit algorithms a…
cs.LG2017★ 20 cited
Information Directed Sampling for Stochastic Bandits with Graph Feedback
Fang Liu, Swapna Buccapatnam, Ness Shroff
We consider stochastic multi-armed bandit problems with graph feedback, where the decision maker is allowed to observe the neighboring actions of the chosen action. We allow the gr…