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/

Zendy Plus

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

Zendy Tools

Zendy Open

Reinforcement learning has gained wide popularity as a technique forsimulation-driven approximate dynamic programming. A less known aspect is thatthe very reasons that make it effective in dynamic programming can also beleveraged for using it for distributed schemes for certain matrix computationsinvolving non-negative matrices. In this spirit, we propose a reinforcementlearning algorithm for PageRank computation that is fashioned after analogousschemes for approximate dynamic programming. The algorithm has the advantage ofease of distributed implementation and more importantly, of being model-free,i.e., not dependent on any specific assumptions about the transitionprobabilities in the random web-surfer model. We analyze its convergence andfinite time behavior and present some supporting numerical experiments.

Reinforcement Learning for Matrix Computations: PageRank as an Example