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

While quantum reinforcement learning (RL) has attracted a surge of attentionrecently, its theoretical understanding is limited. In particular, it remainselusive how to design provably efficient quantum RL algorithms that can addressthe exploration-exploitation trade-off. To this end, we propose a novelUCRL-style algorithm that takes advantage of quantum computing for tabularMarkov decision processes (MDPs) with $S$ states, $A$ actions, and horizon $H$,and establish an $\mathcal{O}(\mathrm{poly}(S, A, H, \log T))$ worst-caseregret for it, where $T$ is the number of episodes. Furthermore, we extend ourresults to quantum RL with linear function approximation, which is capable ofhandling problems with large state spaces. Specifically, we develop a quantumalgorithm based on value target regression (VTR) for linear mixture MDPs with$d$-dimensional linear representation and prove that it enjoys$\mathcal{O}(\mathrm{poly}(d, H, \log T))$ regret. Our algorithms are variantsof UCRL/UCRL-VTR algorithms in classical RL, which also leverage a novelcombination of lazy updating mechanisms and quantum estimation subroutines.This is the key to breaking the $\Omega(\sqrt{T})$-regret barrier in classicalRL. To the best of our knowledge, this is the first work studying the onlineexploration in quantum RL with provable logarithmic worst-case regret.

Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret