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

Multi-player multi-armed bandits (MMAB) study how decentralized playerscooperatively play the same multi-armed bandit so as to maximize their totalcumulative rewards. Existing MMAB models mostly assume when more than oneplayer pulls the same arm, they either have a collision and obtain zerorewards, or have no collision and gain independent rewards, both of which areusually too restrictive in practical scenarios. In this paper, we propose anMMAB with shareable resources as an extension to the collision andnon-collision settings. Each shareable arm has finite shareable resources and a"per-load" reward random variable, both of which are unknown to players. Thereward from a shareable arm is equal to the "per-load" reward multiplied by theminimum between the number of players pulling the arm and the arm's maximalshareable resources. We consider two types of feedback: sharing demandinformation (SDI) and sharing demand awareness (SDA), each of which providesdifferent signals of resource sharing. We design the DPE-SDI and SIC-SDAalgorithms to address the shareable arm problem under these two cases offeedback respectively and prove that both algorithms have logarithmic regretsthat are tight in the number of rounds. We conduct simulations to validate bothalgorithms' performance and show their utilities in wireless networking andedge computing.

Multi-Player Multi-Armed Bandits with Finite Shareable Resources Arms: Learning Algorithms & Applications