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

Online ride-hailing services have become a prevalent transportation systemacross the world. In this paper, we study a challenging problem of how todirect vacant taxis around a city such that supplies and demands can bebalanced in online ride-hailing services. We design a new reward scheme thatconsiders multiple performance metrics of online ride-hailing services. We alsopropose a novel deep reinforcement learning method named Deep-Q-Network withAction Mask (AM-DQN) masking off unnecessary actions in various locations suchthat agents can learn much faster and more efficiently. We conduct extensiveexperiments using a city-scale dataset from Chicago. Several popular heuristicand learning methods are also implemented as baselines for comparison. Theresults of the experiments show that the AM-DQN attains the best performancesof all methods with respect to average failure rate, average waiting time forcustomers, and average idle search time for vacant taxis.

Where to go: Agent Guidance with Deep Reinforcement Learning in A City-Scale Online Ride-Hailing Service