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

The choice of the control frequency of a system has a relevant impact on theability of reinforcement learning algorithms to learn a highly performingpolicy. In this paper, we introduce the notion of action persistence thatconsists in the repetition of an action for a fixed number of decision steps,having the effect of modifying the control frequency. We start analyzing howaction persistence affects the performance of the optimal policy, and then wepresent a novel algorithm, Persistent Fitted Q-Iteration (PFQI), that extendsFQI, with the goal of learning the optimal value function at a givenpersistence. After having provided a theoretical study of PFQI and a heuristicapproach to identify the optimal persistence, we present an experimentalcampaign on benchmark domains to show the advantages of action persistence andproving the effectiveness of our persistence selection method.

Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning