English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In the problem of (binary) contextual bandits with knapsacks (CBwK), theagent receives an i.i.d. context in each of the $T$ rounds and chooses anaction, resulting in a random reward and a random consumption of resources thatare related to an i.i.d. external factor. The agent's goal is to maximize theaccumulated reward under the initial resource constraints. In this work, wecombine the re-solving heuristic, which proved successful in revenuemanagement, with distribution estimation techniques to solve this problem. Weconsider two different information feedback models, with full and partialinformation, which vary in the difficulty of getting a sample of the externalfactor. Under both information feedback settings, we achieve two-way results:(1) For general problems, we show that our algorithm gets an $\widetildeO(T^{\alpha_u} + T^{\alpha_v} + T^{1/2})$ regret against the fluid benchmark.Here, $\alpha_u$ and $\alpha_v$ reflect the complexity of the context andexternal factor distributions, respectively. This result is comparable toexisting results. (2) When the fluid problem is linear programming with aunique and non-degenerate optimal solution, our algorithm leads to an$\widetilde O(1)$ regret. To the best of our knowledge, this is the first$\widetilde O(1)$ regret result in the CBwK problem regardless of informationfeedback models. We further use numerical experiments to verify our results.

On the Re-Solving Heuristic for (Binary) Contextual Bandits with Knapsacks