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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We investigate the Multi-Armed Bandit problem with Temporally-PartitionedRewards (TP-MAB) setting in this paper. In the TP-MAB setting, an agent willreceive subsets of the reward over multiple rounds rather than the entirereward for the arm all at once. In this paper, we introduce a generalformulation of how an arm's cumulative reward is distributed across severalrounds, called Beta-spread property. Such a generalization is needed to be ableto handle partitioned rewards in which the maximum reward per round is notdistributed uniformly across rounds. We derive a lower bound on the TP-MABproblem under the assumption that Beta-spread holds. Moreover, we provide analgorithm TP-UCB-FR-G, which uses the Beta-spread property to improve theregret upper bound in some scenarios. By generalizing how the cumulative rewardis distributed, this setting is applicable in a broader range of applications.

Generalizing distribution of partial rewards for multi-armed bandits with temporally-partitioned rewards