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

Motivated by the episodic version of the classical inventory control problem,we propose a new Q-learning-based algorithm, Elimination-Based Half-Q-Learning(HQL), that enjoys improved efficiency over existing algorithms for a widevariety of problems in the one-sided-feedback setting. We also provide asimpler variant of the algorithm, Full-Q-Learning (FQL), for the full-feedbacksetting. We establish that HQL incurs $ \tilde{\mathcal{O}}(H^3\sqrt{ T})$regret and FQL incurs $\tilde{\mathcal{O}}(H^2\sqrt{ T})$ regret, where $H$ isthe length of each episode and $T$ is the total length of the horizon. Theregret bounds are not affected by the possibly huge state and action space. Ournumerical experiments demonstrate the superior efficiency of HQL and FQL, andthe potential to combine reinforcement learning with richer feedback models.

Provably More Efficient Q-Learning in the One-Sided-Feedback/Full-Feedback Settings