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

For infinite-horizon average-cost criterion problems, we present severalapproximation and reinforcement learning results for Markov Decision Processeswith standard Borel spaces. Toward this end, (i) we first provide adiscretization based approximation method for fully observed Markov DecisionProcesses (MDPs) with continuous spaces under average cost criteria, and weprovide error bounds for the approximations when the dynamics are only weaklycontinuous under certain ergodicity assumptions. In particular, we relax thetotal variation condition given in prior work to weak continuity as well asWasserstein continuity conditions. (ii) We provide synchronous and asynchronousQ-learning algorithms for continuous spaces via quantization, and establishtheir convergence. (iii) We show that the convergence is to the optimal Qvalues of the finite approximate models constructed via quantization. OurQ-learning convergence results and their convergence to near optimality are newfor continuous spaces, and the proof method is new even for finite spaces, toour knowledge.

Q-Learning for Continuous State and Action MDPs under Average Cost Criteria