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 open streets initiative "opens" streets to pedestrians and bicyclists byclosing them to cars and trucks. The initiative, adopted by many cities acrossNorth America, increases community space in urban environments. But could openstreets also make cities safer and less congested? We study this question byframing the choice of which streets to open as a reinforcement learningproblem. In order to simulate the impact of opening streets, we first comparemodels for predicting vehicle collisions given network and temporal data. Wefind that a recurrent graph neural network, leveraging the graph structure andthe short-term temporal dependence of the data, gives the best predictiveperformance. Then, with the ability to simulate collisions and traffic, weframe a reinforcement learning problem to find which streets to open. Wecompare the streets in the NYC Open Streets program to those proposed by aQ-learning algorithm. We find that the streets proposed by the Q-learningalgorithm have reliably better outcomes, while streets in the program havesimilar outcomes to randomly selected streets. We present our work as a steptoward principally choosing which streets to open for safer and less congestedcities. All our code and data are available on Github.

I Open at the Close: A Deep Reinforcement Learning Evaluation of Open Streets Initiatives