Matches in SemOpenAlex for { <https://semopenalex.org/work/W2899703365> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2899703365 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." @default.
- W2899703365 created "2018-11-16" @default.
- W2899703365 creator A5010419481 @default.
- W2899703365 creator A5066808156 @default.
- W2899703365 creator A5068254472 @default.
- W2899703365 creator A5077046363 @default.
- W2899703365 creator A5085579946 @default.
- W2899703365 date "2018-12-01" @default.
- W2899703365 modified "2023-10-02" @default.
- W2899703365 title "Optimizing Taxi Carpool Policies via Reinforcement Learning and Spatio-Temporal Mining" @default.
- W2899703365 cites W1558470758 @default.
- W2899703365 cites W1910491193 @default.
- W2899703365 cites W1993912146 @default.
- W2899703365 cites W2063709997 @default.
- W2899703365 cites W2073209910 @default.
- W2899703365 cites W2077963913 @default.
- W2899703365 cites W2081942684 @default.
- W2899703365 cites W2093829413 @default.
- W2899703365 cites W2144475703 @default.
- W2899703365 cites W2145339207 @default.
- W2899703365 cites W2156767060 @default.
- W2899703365 cites W2257979135 @default.
- W2899703365 cites W2516072053 @default.
- W2899703365 cites W2539085224 @default.
- W2899703365 cites W2565919573 @default.
- W2899703365 cites W27224072 @default.
- W2899703365 cites W2809128166 @default.
- W2899703365 cites W2809623940 @default.
- W2899703365 cites W2964098640 @default.
- W2899703365 cites W2964273174 @default.
- W2899703365 cites W32403112 @default.
- W2899703365 doi "https://doi.org/10.1109/bigdata.2018.8622481" @default.
- W2899703365 hasPublicationYear "2018" @default.
- W2899703365 type Work @default.
- W2899703365 sameAs 2899703365 @default.
- W2899703365 citedByCount "32" @default.
- W2899703365 countsByYear W28997033652019 @default.
- W2899703365 countsByYear W28997033652020 @default.
- W2899703365 countsByYear W28997033652021 @default.
- W2899703365 countsByYear W28997033652022 @default.
- W2899703365 countsByYear W28997033652023 @default.
- W2899703365 crossrefType "proceedings-article" @default.
- W2899703365 hasAuthorship W2899703365A5010419481 @default.
- W2899703365 hasAuthorship W2899703365A5066808156 @default.
- W2899703365 hasAuthorship W2899703365A5068254472 @default.
- W2899703365 hasAuthorship W2899703365A5077046363 @default.
- W2899703365 hasAuthorship W2899703365A5085579946 @default.
- W2899703365 hasBestOaLocation W28997033652 @default.
- W2899703365 hasConcept C119857082 @default.
- W2899703365 hasConcept C127413603 @default.
- W2899703365 hasConcept C154945302 @default.
- W2899703365 hasConcept C22212356 @default.
- W2899703365 hasConcept C2779888511 @default.
- W2899703365 hasConcept C2780427980 @default.
- W2899703365 hasConcept C41008148 @default.
- W2899703365 hasConcept C50644808 @default.
- W2899703365 hasConcept C60229501 @default.
- W2899703365 hasConcept C76155785 @default.
- W2899703365 hasConcept C79337645 @default.
- W2899703365 hasConcept C97541855 @default.
- W2899703365 hasConceptScore W2899703365C119857082 @default.
- W2899703365 hasConceptScore W2899703365C127413603 @default.
- W2899703365 hasConceptScore W2899703365C154945302 @default.
- W2899703365 hasConceptScore W2899703365C22212356 @default.
- W2899703365 hasConceptScore W2899703365C2779888511 @default.
- W2899703365 hasConceptScore W2899703365C2780427980 @default.
- W2899703365 hasConceptScore W2899703365C41008148 @default.
- W2899703365 hasConceptScore W2899703365C50644808 @default.
- W2899703365 hasConceptScore W2899703365C60229501 @default.
- W2899703365 hasConceptScore W2899703365C76155785 @default.
- W2899703365 hasConceptScore W2899703365C79337645 @default.
- W2899703365 hasConceptScore W2899703365C97541855 @default.
- W2899703365 hasLocation W28997033651 @default.
- W2899703365 hasLocation W28997033652 @default.
- W2899703365 hasOpenAccess W2899703365 @default.
- W2899703365 hasPrimaryLocation W28997033651 @default.
- W2899703365 hasRelatedWork W3022038857 @default.
- W2899703365 hasRelatedWork W338500336 @default.
- W2899703365 hasRelatedWork W4319083788 @default.
- W2899703365 hasRelatedWork W562315929 @default.
- W2899703365 hasRelatedWork W564366942 @default.
- W2899703365 hasRelatedWork W582345564 @default.
- W2899703365 hasRelatedWork W633524360 @default.
- W2899703365 hasRelatedWork W836230674 @default.
- W2899703365 hasRelatedWork W1629725936 @default.
- W2899703365 hasRelatedWork W2564049021 @default.
- W2899703365 isParatext "false" @default.
- W2899703365 isRetracted "false" @default.
- W2899703365 magId "2899703365" @default.
- W2899703365 workType "article" @default.