Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1066102

Application of Deep Reinforcement Learning in Traffic Signal Control: An Overview and Impact of Open Traffic Data


Gregurić, Martin; Vujić, Miroslav; Alexopoulos, Charalampos; Miletić, Mladen
Application of Deep Reinforcement Learning in Traffic Signal Control: An Overview and Impact of Open Traffic Data // Applied Sciences-Basel, 10 (2020), 11; 4011, 25 doi:10.3390/app10114011 (međunarodna recenzija, pregledni rad, znanstveni)


CROSBI ID: 1066102 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Application of Deep Reinforcement Learning in Traffic Signal Control: An Overview and Impact of Open Traffic Data

Autori
Gregurić, Martin ; Vujić, Miroslav ; Alexopoulos, Charalampos ; Miletić, Mladen

Izvornik
Applied Sciences-Basel (2076-3417) 10 (2020), 11; 4011, 25

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, pregledni rad, znanstveni

Ključne riječi
deep reinforcement learning ; adaptive traffic signal control ; multi-agent systems ; intelligent mobility ; deep neural networks ; open traffic data ; big data

Sažetak
Persistent congestions which are varying in strength and duration in the dense traffic networks are the most prominent obstacle towards sustainable mobility. Those types of congestions cannot be adequately resolved by the traditional Adaptive Traffic Signal Control (ATSC). The introduction of Reinforcement Learning (RL) in ATSC as tackled those types of congestions by using on-line learning, which is based on the trial and error approach. Furthermore, RL is prone to the dimensionality curse related to the state–action space size based on which a non-linear quality function is derived. The Deep Reinforcement Learning (DRL) framework uses Deep Neural Networks (DNN) to digest raw traffic data to approximate the quality function of RL. This paper provides a comprehensive analysis of the most recent DRL approaches used for the ATSC algorithm design. Special emphasis is set to overview of the traffic state representation and multi-agent DRL frameworks applied for the large traffic networks. Best practices are provided for choosing the adequate DRL model, hyper- parameters tuning, and model architecture design. Finally, this paper provides a discussion about the importance of the open traffic data concept for the extensive application of DRL in the real world ATSC.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Tehnologija prometa i transport, Informacijske i komunikacijske znanosti



POVEZANOST RADA


Projekti:
EK-H2020-857592 - Twinning koordinacijska akcija u području otvorenih podataka (TODO) (Čavrak, Igor; Tutić, Dražen; Šalamon, Dragica; Musa, Anamarija; Vujić, Miroslav; Žajdela Hrustek, Nikolina; Kuveždić Divjak, Ana, EK - H2020-WIDESPREAD-2018-03) ( POIROT)

Ustanove:
Fakultet prometnih znanosti, Zagreb

Profili:

Avatar Url Mladen Miletić (autor)

Avatar Url Miroslav Vujić (autor)

Avatar Url Martin Gregurić (autor)

Citiraj ovu publikaciju

Gregurić, Martin; Vujić, Miroslav; Alexopoulos, Charalampos; Miletić, Mladen
Application of Deep Reinforcement Learning in Traffic Signal Control: An Overview and Impact of Open Traffic Data // Applied Sciences-Basel, 10 (2020), 11; 4011, 25 doi:10.3390/app10114011 (međunarodna recenzija, pregledni rad, znanstveni)
Gregurić, M., Vujić, M., Alexopoulos, C. & Miletić, M. (2020) Application of Deep Reinforcement Learning in Traffic Signal Control: An Overview and Impact of Open Traffic Data. Applied Sciences-Basel, 10 (11), 4011, 25 doi:10.3390/app10114011.
@article{article, year = {2020}, pages = {25}, DOI = {10.3390/app10114011}, chapter = {4011}, keywords = {deep reinforcement learning, adaptive traffic signal control, multi-agent systems, intelligent mobility, deep neural networks, open traffic data, big data}, journal = {Applied Sciences-Basel}, doi = {10.3390/app10114011}, volume = {10}, number = {11}, issn = {2076-3417}, title = {Application of Deep Reinforcement Learning in Traffic Signal Control: An Overview and Impact of Open Traffic Data}, keyword = {deep reinforcement learning, adaptive traffic signal control, multi-agent systems, intelligent mobility, deep neural networks, open traffic data, big data}, chapternumber = {4011} }
@article{article, year = {2020}, pages = {25}, DOI = {10.3390/app10114011}, chapter = {4011}, keywords = {deep reinforcement learning, adaptive traffic signal control, multi-agent systems, intelligent mobility, deep neural networks, open traffic data, big data}, journal = {Applied Sciences-Basel}, doi = {10.3390/app10114011}, volume = {10}, number = {11}, issn = {2076-3417}, title = {Application of Deep Reinforcement Learning in Traffic Signal Control: An Overview and Impact of Open Traffic Data}, keyword = {deep reinforcement learning, adaptive traffic signal control, multi-agent systems, intelligent mobility, deep neural networks, open traffic data, big data}, chapternumber = {4011} }

Časopis indeksira:


  • Current Contents Connect (CCC)
  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus


Citati





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font