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

Bus bunching is a natural-occurring phenomenon that undermines the efficiencyand stability of the public transportation system. The mainstream solutionscontrol the bus to intentionally stay longer at certain stations. Existingcontrol methods include conventional methods that provide a formula tocalculate the control time and reinforcement learning (RL) methods thatdetermine the control policy through repeated interactions with the system. Inthis paper, we propose an integrated proximal policy optimization model withdual-headway (IPPO-DH). IPPO-DH integrates the conventional headway controlwith reinforcement learning, so that it acquires the advantages of bothalgorithms -- it is more efficient in normal environments and more stable inharsh ones. To demonstrate such an advantage, we design a bus simulationenvironment and compare IPPO-DH with RL and several conventional methods. Theresults show that the proposed model maintains the application value of theconventional method by avoiding the instability of the RL method in certainenvironments, and improves the efficiency compared with the conventionalcontrol, shedding new light on real-world bus transit system optimization.

Integrating Conventional Headway Control with Reinforcement Learning to Avoid Bus Bunching