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 optimization of traffic signal control (TSC) is critical for an efficienttransportation system. In recent years, reinforcement learning (RL) techniqueshave emerged as a popular approach for TSC and show promising results forhighly adaptive control. However, existing RL-based methods suffer from notablypoor real-world applicability and hardly have any successful deployments. Thereasons for such failures are mostly due to the reliance on over-idealizedtraffic simulators for policy optimization, as well as using unrealisticfine-grained state observations and reward signals that are not directlyobtainable from real-world sensors. In this paper, we propose a fullyData-Driven and simulator-free framework for realistic Traffic Signal Control(D2TSC). Specifically, we combine well-established traffic flow theory withmachine learning to construct a reward inference model to infer the rewardsignals from coarse-grained traffic data. With the inferred rewards, we furtherpropose a sample-efficient offline RL method to enable direct signal controlpolicy learning from historical offline datasets of real-world intersections.To evaluate our approach, we collect historical traffic data from a real-worldintersection, and develop a highly customized simulation environment thatstrictly follows real data characteristics. We demonstrate through extensiveexperiments that our approach achieves superior performance over conventionaland offline RL baselines, and also enjoys much better real-world applicability.

A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning