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

The use of Reinforcement Learning in real-world scenarios is strongly limitedby issues of scale. Most RL learning algorithms are unable to deal withproblems composed of hundreds or sometimes even dozens of possible actions, andtherefore cannot be applied to many real-world problems. We consider the RLproblem in the supervised classification framework where the optimal policy isobtained through a multiclass classifier, the set of classes being the set ofactions of the problem. We introduce error-correcting output codes (ECOCs) inthis setting and propose two new methods for reducing complexity when usingrollouts-based approaches. The first method consists in using an ECOC-basedclassifier as the multiclass classifier, reducing the learning complexity fromO(A2) to O(Alog(A)). We then propose a novel method that profits from theECOC's coding dictionary to split the initial MDP into O(log(A)) seperatetwo-action MDPs. This second method reduces learning complexity even further,from O(A2) to O(log(A)), thus rendering problems with large action setstractable. We finish by experimentally demonstrating the advantages of ourapproach on a set of benchmark problems, both in speed and performance.

Fast Reinforcement Learning with Large Action Sets using Error-Correcting Output Codes for MDP Factorization