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

We develop a regression based primal-dual martingale approach for solvingfinite time horizon MDPs with general state and action space. As a result, ourmethod allows for the construction of tight upper and lower biasedapproximations of the value functions, and, provides tight approximations tothe optimal policy. In particular, we prove tight error bounds for theestimated duality gap featuring polynomial dependence on the time horizon, andsublinear dependence on the cardinality/dimension of the possibly infinitestate and action space.From a computational point of view the proposed methodis efficient since, in contrast to usual duality-based methods for optimalcontrol problems in the literature, the Monte Carlo procedures here involved donot require nested simulations.

Primal-dual regression approach for Markov decision processes with general state and action space