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

Existing data-driven and feedback traffic control strategies do not considerthe heterogeneity of real-time data measurements. Besides, traditionalreinforcement learning (RL) methods for traffic control usually converge slowlyfor lacking data efficiency. Moreover, conventional optimal perimeter controlschemes require exact knowledge of the system dynamics and thus would befragile to endogenous uncertainties. To handle these challenges, this workproposes an integral reinforcement learning (IRL) based approach to learningthe macroscopic traffic dynamics for adaptive optimal perimeter control. Thiswork makes the following primary contributions to the transportationliterature: (a) A continuous-time control is developed with discrete gainupdates to adapt to the discrete-time sensor data. (b) To reduce the samplingcomplexity and use the available data more efficiently, the experience replay(ER) technique is introduced to the IRL algorithm. (c) The proposed methodrelaxes the requirement on model calibration in a "model-free" manner thatenables robustness against modeling uncertainty and enhances the real-timeperformance via a data-driven RL algorithm. (d) The convergence of theIRL-based algorithms and the stability of the controlled traffic dynamics areproven via the Lyapunov theory. The optimal control law is parameterized andthen approximated by neural networks (NN), which moderates the computationalcomplexity. Both state and input constraints are considered while no modellinearization is required. Numerical examples and simulation experiments arepresented to verify the effectiveness and efficiency of the proposed method.

Data efficient reinforcement learning and adaptive optimal perimeter control of network traffic dynamics