Scipediacontent: Scipediacontent moved page Draft Content 289201132 to Jindal et al 2018a

2021-02-03T19:43:21Z

Scipediacontent moved page Draft Content 289201132 to Jindal et al 2018a

Scipediacontent: Created page with " == Abstract == In this paper, we develop a reinforcement learning (RL) based system to learn an effective policy for carpooling that maximizes transportation efficiency so t..."

2021-02-03T19:43:17Z

Created page with " == Abstract == In this paper, we develop a reinforcement learning (RL) based system to learn an effective policy for carpooling that maximizes transportation efficiency so t..."

New page

== Abstract ==

In this paper, we develop a reinforcement learning (RL) based system to learn an effective policy for carpooling that maximizes transportation efficiency so that fewer cars are required to fulfill the given amount of trip demand. For this purpose, first, we develop a deep neural network model, called ST-NN (Spatio-Temporal Neural Network), to predict taxi trip time from the raw GPS trip data. Secondly, we develop a carpooling simulation environment for RL training, with the output of ST-NN and using the NYC taxi trip dataset. In order to maximize transportation efficiency and minimize traffic congestion, we choose the effective distance covered by the driver on a carpool trip as the reward. Therefore, the more effective distance a driver achieves over a trip (i.e. to satisfy more trip demand) the higher the efficiency and the less will be the traffic congestion. We compared the performance of RL learned policy to a fixed policy (which always accepts carpool) as a baseline and obtained promising results that are interpretable and demonstrate the advantage of our RL approach. We also compare the performance of ST-NN to that of state-of-the-art travel time estimation methods and observe that ST-NN significantly improves the prediction performance and is more robust to outliers.

Comment: Accepted at IEEE International Conference on Big Data 2018. arXiv admin note: text overlap with arXiv:1710.04350

== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/1811.04345 http://arxiv.org/abs/1811.04345]

* [http://arxiv.org/pdf/1811.04345 http://arxiv.org/pdf/1811.04345]

* [http://xplorestaging.ieee.org/ielx7/8610059/8621858/08622481.pdf?arnumber=8622481 http://xplorestaging.ieee.org/ielx7/8610059/8621858/08622481.pdf?arnumber=8622481],
: [http://dx.doi.org/10.1109/bigdata.2018.8622481 http://dx.doi.org/10.1109/bigdata.2018.8622481]

* [https://dblp.uni-trier.de/db/journals/corr/corr1811.html#abs-1811-04345 https://dblp.uni-trier.de/db/journals/corr/corr1811.html#abs-1811-04345],
: [https://academic.microsoft.com/#/detail/2899703365 https://academic.microsoft.com/#/detail/2899703365]

← Older revision	Revision as of 19:43, 3 February 2021
(No difference)

Jindal et al 2018a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 289201132 to Jindal et al 2018a

Scipediacontent: Created page with " == Abstract == In this paper, we develop a reinforcement learning (RL) based system to learn an effective policy for carpooling that maximizes transportation efficiency so t..."