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

Napredna pretraga

Pregled bibliografske jedinice broj: 1112831

Learning Near-Optimal Broadcasting Intervals in Decentralized Multi-Agent Systems using Online Least-Square Policy Iteration


Palunko, Ivana; Tolić, Domagoj; Prkačin, Vicko
Learning Near-Optimal Broadcasting Intervals in Decentralized Multi-Agent Systems using Online Least-Square Policy Iteration // IET control theory and applications, 15 (2021), 8; 1054-1067 doi:10.1049/cth2.12102 (međunarodna recenzija, članak, znanstveni)


CROSBI ID: 1112831 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Learning Near-Optimal Broadcasting Intervals in Decentralized Multi-Agent Systems using Online Least-Square Policy Iteration

Autori
Palunko, Ivana ; Tolić, Domagoj ; Prkačin, Vicko

Izvornik
IET control theory and applications (1751-8644) 15 (2021), 8; 1054-1067

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
multi-agent systems, decentralized control, learning (artificial intelligence), optimal control

Sažetak
Here, agents learn how often to exchange information with neighbours in cooperative multi‐ agent systems (MASs) such that their linear quadratic regulator (LQR)‐like performance indices are minimized. The investigated LQR‐like cost functions capture trade‐offs between the energy consumption of each agent and MAS local control performance in the presence of exogenous disturbances, delayed and noisy data. Agent energy consumption is critical for prolonging the MAS mission and is composed of both control (e.g. acceleration, velocity) and communication efforts. Taking provably stabilizing upper bounds on broadcasting intervals as optimization constraints, an online off‐policy model‐free learning algorithm based on least square policy iteration (LSPI) to minimize the cost function of each agent is employed. Consequently, the obtained broadcasting intervals adapt to the most recent information (e.g. delayed and noisy agents' inputs and/or outputs) received from neighbours whilst provably stabilize the MAS. Chebyshev polynomials are utilized as the approximator in the LSPI whereas Kalman filtering handles sampled, corrupted, and delayed data. Subsequently, convergence and near‐optimality of our LSPI scheme are inspected. The proposed methodology is verified experimentally using an inexpensive motion capture system and nano quadrotors.

Izvorni jezik
Engleski

Znanstvena područja
Matematika, Elektrotehnika, Računarstvo



POVEZANOST RADA


Projekti:
IP-2016-06-2468 - Upravljanje dinamičkim sustavima (ConDyS) (Lazar, Martin, HRZZ - 2016-06) ( CroRIS)
EK-KF-KK.01.1.1.01.0009-2 - Napredne metode i tehnologije u znanosti o podatcima i kooperativnim sustavima - IJ za napredne kooperativne sustave (DATACROSS) (Petrović, Ivan; Šmuc, Tomislav, EK - KK.01.1.1.01) ( CroRIS)

Ustanove:
Sveučilište u Dubrovniku,
RIT Croatia, Dubrovnik

Profili:

Avatar Url Vicko Prkačin (autor)

Avatar Url Ivana Palunko (autor)

Avatar Url Domagoj Tolić (autor)

Poveznice na cjeloviti tekst rada:

doi ietresearch.onlinelibrary.wiley.com

Citiraj ovu publikaciju:

Palunko, Ivana; Tolić, Domagoj; Prkačin, Vicko
Learning Near-Optimal Broadcasting Intervals in Decentralized Multi-Agent Systems using Online Least-Square Policy Iteration // IET control theory and applications, 15 (2021), 8; 1054-1067 doi:10.1049/cth2.12102 (međunarodna recenzija, članak, znanstveni)
Palunko, I., Tolić, D. & Prkačin, V. (2021) Learning Near-Optimal Broadcasting Intervals in Decentralized Multi-Agent Systems using Online Least-Square Policy Iteration. IET control theory and applications, 15 (8), 1054-1067 doi:10.1049/cth2.12102.
@article{article, author = {Palunko, Ivana and Toli\'{c}, Domagoj and Prka\v{c}in, Vicko}, year = {2021}, pages = {1054-1067}, DOI = {10.1049/cth2.12102}, keywords = {multi-agent systems, decentralized control, learning (artificial intelligence), optimal control}, journal = {IET control theory and applications}, doi = {10.1049/cth2.12102}, volume = {15}, number = {8}, issn = {1751-8644}, title = {Learning Near-Optimal Broadcasting Intervals in Decentralized Multi-Agent Systems using Online Least-Square Policy Iteration}, keyword = {multi-agent systems, decentralized control, learning (artificial intelligence), optimal control} }
@article{article, author = {Palunko, Ivana and Toli\'{c}, Domagoj and Prka\v{c}in, Vicko}, year = {2021}, pages = {1054-1067}, DOI = {10.1049/cth2.12102}, keywords = {multi-agent systems, decentralized control, learning (artificial intelligence), optimal control}, journal = {IET control theory and applications}, doi = {10.1049/cth2.12102}, volume = {15}, number = {8}, issn = {1751-8644}, title = {Learning Near-Optimal Broadcasting Intervals in Decentralized Multi-Agent Systems using Online Least-Square Policy Iteration}, keyword = {multi-agent systems, decentralized control, learning (artificial intelligence), optimal control} }

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