Nalazite se na CroRIS probnoj okolini. Ovdje evidentirani podaci neće biti pohranjeni u Informacijskom sustavu znanosti RH. Ako je ovo greška, CroRIS produkcijskoj okolini moguće je pristupi putem poveznice www.croris.hr
izvor podataka: crosbi

A Comparison of Different State Representations for Reinforcement Learning Based Variable Speed Limit Control (CROSBI ID 663537)

Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija

Kušić, Krešimir ; Ivanjko, Edouard ; Gregurić, Martin A Comparison of Different State Representations for Reinforcement Learning Based Variable Speed Limit Control // Proceedings of MED-2018. Mediterranean Control Association, 2018. str. 266-271 doi: 10.1109/MED.2018.8442986

Podaci o odgovornosti

Kušić, Krešimir ; Ivanjko, Edouard ; Gregurić, Martin

engleski

A Comparison of Different State Representations for Reinforcement Learning Based Variable Speed Limit Control

Variable Speed Limit Control (VSLC) is one control method for alleviating congestions on urban motorways. Machine learning techniques, like Reinforcement Learning (RL), are a promising alternative for setting up VSLC because an optimal control policy can be achieved with a smaller computational burden in comparison with optimal control approaches. A drawback is a large number of learning iterations and the problem of the exponential expansion of the state space dimension. This can be solved with function approximation techniques. Three different approaches for feature-based state representation in RL based VSLC are compared in this paper regarding the convergence of Total Time Spent. The microscopic traffic simulator VISSIM with a representative traffic model is used to evaluate the compared approaches. Results show that function approximation methods outperform RL based VSLC formulated with a lookup table by an average improvement of 10 %, where feature extraction methods (Coarse and Tile) coding showed slightly faster learning rate.

Intelligent transportation systems, Intelligent control systems, Variable speed limit control, Reinforcement learning, Tile coding, Coarse coding, RBF

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

Podaci o prilogu

266-271.

2018.

objavljeno

10.1109/MED.2018.8442986

Podaci o matičnoj publikaciji

Proceedings of MED-2018

Mediterranean Control Association

978-1-5090-4532-7

Podaci o skupu

26th Mediterranean Conference on Control and Automation (MED 2018)

predavanje

19.06.2018-22.06.2018

Zadar, Hrvatska

Povezanost rada

Trošak objave rada u otvorenom pristupu

Elektrotehnika, Računarstvo, Tehnologija prometa i transport

Poveznice
Indeksiranost