Asymptotically Optimal Problem-Dependent Bandit Policies for Transfer Learning
Not on the map. Why?
Abstract (arXiv)
We study the non-contextual multi-armed bandit problem in a transfer learning setting: before any pulls, the learner is given N'_k i.i.d. samples from each source distribution nu'_k, and the true target distributions nu_k lie within a known distance bound d_k(nu_k, nu'_k) <= L_k. In this framework, we first derive a problem-dependent asymptotic lower bound on cumulative regret that extends the classical Lai-Robbins result to incorporate the transfer parameters (d_k, L_k, N'_k). We then propose KL-UCB-Transfer, a simple index policy that matches this new bound in the Gaussian case. Finally, we validate our approach via simulations, showing that KL-UCB-Transfer significantly outperforms the no-prior baseline when source and target distributions are sufficiently close.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 21 references that are in the map. First posted on arXiv 23 Sep 2025.
Builds on
6 of 21 references.
References · 6
- 2013Sequential Transfer in Multi-armed Bandit with Finite Set of Modelscited by 38
- 2022Transfer Learning for Contextual Multi-armed Banditscited by 24
- 2025Transfer Learning in Latent Contextual Bandits with Covariate Shift Through Causal Transportabilitycited by 4
- 2022Thompson Sampling for Robust Transfer in Multi-Task Banditscited by 3
- 2024Transfer in Sequential Multi-armed Bandits via Reward Samplescited by 2
- 2024Exploiting Adjacent Similarity in Multi-Armed Bandit Tasks via Transfer of Reward Samplescited by 1
Built on by
Not cited yet.