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

This paper gives the first polynomial-time algorithm for tabular MarkovDecision Processes (MDP) that enjoys a regret bound \emph{independent on theplanning horizon}. Specifically, we consider tabular MDP with $S$ states, $A$actions, a planning horizon $H$, total reward bounded by $1$, and the agentplays for $K$ episodes. We design an algorithm that achieves an$O\left(\mathrm{poly}(S,A,\log K)\sqrt{K}\right)$ regret in contrast toexisting bounds which either has an additional $\mathrm{polylog}(H)$dependency~\citep{zhang2020reinforcement} or has an exponential dependency on$S$~\citep{li2021settling}. Our result relies on a sequence of new structurallemmas establishing the approximation power, stability, and concentrationproperty of stationary policies, which can have applications in other problemsrelated to Markov chains.

Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies