Thompson Sampling for Robust Transfer in Multi-Task Bandits. (arXiv:2206.08556v1 [cs.LG])

Web: http://arxiv.org/abs/2206.08556

We study the problem of online multi-task learning where the tasks are
performed within similar but not necessarily identical multi-armed bandit
environments. In particular, we study how a learner can improve its overall
performance across multiple related tasks through robust transfer of knowledge.
While an upper confidence bound (UCB)-based algorithm has recently been shown
to achieve nearly-optimal performance guarantees in a setting where all tasks
are solved concurrently, it remains unclear whether Thompson sampling (TS)
algorithms, which have superior empirical …

arxiv lg sampling transfer