Deep Reinforcement Learning for Ride-Sharing Dispatching and Repositioning
Abstract
In this demo, we will present a simulation-based human-computer interaction of deep reinforcement learning in action on order dispatching and driver repositioning for ride-sharing. Specifically, we will demonstrate through several specially designed domains how we use deep reinforcement learning to train agents (drivers) to have longer optimization horizon and to cooperate to achieve higher objective values collectively.
Cite
Text
Qin et al. "Deep Reinforcement Learning for Ride-Sharing Dispatching and Repositioning." International Joint Conference on Artificial Intelligence, 2019. doi:10.24963/IJCAI.2019/958Markdown
[Qin et al. "Deep Reinforcement Learning for Ride-Sharing Dispatching and Repositioning." International Joint Conference on Artificial Intelligence, 2019.](https://mlanthology.org/ijcai/2019/qin2019ijcai-deep/) doi:10.24963/IJCAI.2019/958BibTeX
@inproceedings{qin2019ijcai-deep,
title = {{Deep Reinforcement Learning for Ride-Sharing Dispatching and Repositioning}},
author = {Qin, Zhiwei (Tony) and Tang, Xiaocheng and Jiao, Yan and Zhang, Fan and Wang, Chenxi and Li, Qun (Tracy)},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2019},
pages = {6566-6568},
doi = {10.24963/IJCAI.2019/958},
url = {https://mlanthology.org/ijcai/2019/qin2019ijcai-deep/}
}