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 classic DQN algorithm is limited by the overestimation bias of thelearned Q-function. Subsequent algorithms have proposed techniques to reducethis problem, without fully eliminating it. Recently, the Maxmin and EnsembleQ-learning algorithms have used different estimates provided by the ensemblesof learners to reduce the overestimation bias. Unfortunately, these learnerscan converge to the same point in the parametric or representation space,falling back to the classic single neural network DQN. In this paper, wedescribe a regularization technique to maximize ensemble diversity in thesealgorithms. We propose and compare five regularization functions inspired fromeconomics theory and consensus optimization. We show that the regularizedapproach significantly outperforms the Maxmin and Ensemble Q-learningalgorithms as well as non-ensemble baselines.

Preventing Value Function Collapse in Ensemble {Q}-Learning by Maximizing Representation Diversity