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

In this work we present a new method of black-box optimization and constraintsatisfaction. Existing algorithms that have attempted to solve this problem areunable to consider multiple modes, and are not able to adapt to changes inenvironment dynamics. To address these issues, we developed a modifiedCross-Entropy Method (CEM) that uses a masked auto-regressive neural networkfor modeling uniform distributions over the solution space. We train the modelusing maximum entropy policy gradient methods from Reinforcement Learning. Ouralgorithm is able to express complicated solution spaces, thus allowing it totrack a variety of different solution regions. We empirically compare ouralgorithm with variations of CEM, including one with a Gaussian prior withfixed variance, and demonstrate better performance in terms of: number ofdiverse solutions, better mode discovery in multi-modal problems, and bettersample efficiency in certain cases.

GACEM: Generalized Autoregressive Cross Entropy Method for Multi-Modal Black Box Constraint Satisfaction