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

In this paper we consider the problem of obtaining sharp bounds for theperformance of temporal difference (TD) methods with linear functionalapproximation for policy evaluation in discounted Markov Decision Processes. Weshow that a simple algorithm with a universal and instance-independent stepsize together with Polyak-Ruppert tail averaging is sufficient to obtainnear-optimal variance and bias terms. We also provide the respective samplecomplexity bounds. Our proof technique is based on refined error bounds forlinear stochastic approximation together with the novel stability result forthe product of random matrices that arise from the TD-type recurrence.

Finite-Sample Analysis of the Temporal Difference Learning