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

Shared e-mobility services have been widely tested and piloted in citiesacross the globe, and already woven into the fabric of modern urban planning.This paper studies a practical yet important problem in those systems: how todeploy and manage their infrastructure across space and time, so that theservices are ubiquitous to the users while sustainable in profitability.However, in real-world systems evaluating the performance of differentdeployment strategies and then finding the optimal plan is prohibitivelyexpensive, as it is often infeasible to conduct many iterations oftrial-and-error. We tackle this by designing a high-fidelity simulationenvironment, which abstracts the key operation details of the shared e-mobilitysystems at fine-granularity, and is calibrated using data collected from thereal-world. This allows us to try out arbitrary deployment plans to learn theoptimal given specific context, before actually implementing any in thereal-world systems. In particular, we propose a novel multi-agent neural searchapproach, in which we design a hierarchical controller to produce tentativedeployment plans. The generated deployment plans are then tested using amulti-simulation paradigm, i.e., evaluated in parallel, where the results areused to train the controller with deep reinforcement learning. With this closedloop, the controller can be steered to have higher probability of generatingbetter deployment plans in future iterations. The proposed approach has beenevaluated extensively in our simulation environment, and experimental resultsshow that it outperforms baselines e.g., human knowledge, and state-of-the-artheuristic-based optimization approaches in both service coverage and netrevenue.

Deployment Optimization for Shared e-Mobility Systems with Multi-agent Deep Neural Search