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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper proposes a reinforcement learning approach for traffic controlwith the adaptive horizon. To build the controller for the traffic network, aQ-learning-based strategy that controls the green light passing time at thenetwork intersections is applied. The controller includes two components: theregular Q-learning controller that controls the traffic light signal, and theadaptive controller that continuously optimizes the action space for theQ-learning algorithm in order to improve the efficiency of the Q-learningalgorithm. The regular Q-learning controller uses the control cost function asa reward function to determine the action to choose. The adaptive controllerexamines the control cost and updates the action space of the controller bydetermining the subset of actions that are most likely to obtain optimalresults and shrinking the action space to that subset. Uncertainties in trafficinflux and turning rate are introduced to test the robustness of the controllerunder a stochastic environment. Compared with those with model predictivecontrol (MPC), the results show that the proposed Q-learning-based controlleroutperforms the MPC method by reaching a stable solution in a shorter periodand achieves lower control costs. The proposed Q-learning-based controller isalso robust under 30% traffic demand uncertainty and 15% turning rateuncertainty.

Reinforcement Learning for Traffic Control with Adaptive Horizon