Transfer Learning for Contextual Multi-armed Bandits. (arXiv:2211.12612v1 [stat.ML])

Motivated by a range of applications, we study in this paper the problem of
transfer learning for nonparametric contextual multi-armed bandits under the
covariate shift model, where we have data collected on source bandits before
the start of the target bandit learning. The minimax rate of convergence for
the cumulative regret is established and a novel transfer learning algorithm
that attains the minimax regret is proposed. The results quantify the
contribution of the data from the source domains for learning …

arxiv multi-armed bandits transfer transfer learning